Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.5053. Min Range: -11.5053
Max Act: 11.5053. Min Act: -0.1700
Data Index: 1547316 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5053. Min Range: -11.5053
Max Act: 11.0678. Min Act: -0.1700
Data Index: 8808294 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5053. Min Range: -11.5053
Max Act: 10.8178. Min Act: -0.1700
Data Index: 4782279 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5053. Min Range: -11.5053
Max Act: 10.7553. Min Act: -0.1700
Data Index: 3651571 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5053. Min Range: -11.5053
Max Act: 10.5678. Min Act: -0.1700
Data Index: 7937900 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5053. Min Range: -11.5053
Max Act: 10.5053. Min Act: -0.1700
Data Index: 8675522 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5053. Min Range: -11.5053
Max Act: 10.3803. Min Act: -0.1700
Data Index: 1635157 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5053. Min Range: -11.5053
Max Act: 10.3803. Min Act: -0.1700
Data Index: 4249813 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5053. Min Range: -11.5053
Max Act: 10.3178. Min Act: -0.1700
Data Index: 4632422 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5053. Min Range: -11.5053
Max Act: 10.1928. Min Act: -0.1700
Data Index: 7407154 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5053. Min Range: -11.5053
Max Act: 10.2553. Min Act: -0.1700
Data Index: 2269109 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5053. Min Range: -11.5053
Max Act: 10.1303. Min Act: -0.1700
Data Index: 2059011 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5053. Min Range: -11.5053
Max Act: 10.1928. Min Act: -0.1700
Data Index: 7127644 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5053. Min Range: -11.5053
Max Act: 10.0053. Min Act: -0.1700
Data Index: 1399253 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5053. Min Range: -11.5053
Max Act: 10.1303. Min Act: -0.1700
Data Index: 2840925 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5053. Min Range: -11.5053
Max Act: 10.0678. Min Act: -0.1700
Data Index: 5971991 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5053. Min Range: -11.5053
Max Act: 10.0053. Min Act: -0.1700
Data Index: 6645131 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5053. Min Range: -11.5053
Max Act: 9.9428. Min Act: -0.1700
Data Index: 8693893 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5053. Min Range: -11.5053
Max Act: 9.9428. Min Act: -0.1700
Data Index: 585387 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5053. Min Range: -11.5053
Max Act: 9.9428. Min Act: -0.1700
Data Index: 7752251 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19