Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5484. Min Range: -3.5484
Max Act: 3.5484. Min Act: -0.1700
Data Index: 5483012 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5484. Min Range: -3.5484
Max Act: 3.4388. Min Act: -0.1700
Data Index: 680357 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5484. Min Range: -3.5484
Max Act: 3.4075. Min Act: -0.1700
Data Index: 6400141 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5484. Min Range: -3.5484
Max Act: 3.4075. Min Act: -0.1700
Data Index: 1546961 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5484. Min Range: -3.5484
Max Act: 3.4075. Min Act: -0.1700
Data Index: 202600 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5484. Min Range: -3.5484
Max Act: 3.3918. Min Act: -0.1700
Data Index: 6144173 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5484. Min Range: -3.5484
Max Act: 3.3761. Min Act: -0.1700
Data Index: 6257021 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5484. Min Range: -3.5484
Max Act: 3.3604. Min Act: -0.1700
Data Index: 1754760 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5484. Min Range: -3.5484
Max Act: 3.3761. Min Act: -0.1700
Data Index: 3317790 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5484. Min Range: -3.5484
Max Act: 3.3447. Min Act: -0.1700
Data Index: 7859248 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5484. Min Range: -3.5484
Max Act: 3.3290. Min Act: -0.1700
Data Index: 2943634 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5484. Min Range: -3.5484
Max Act: 3.3290. Min Act: -0.1700
Data Index: 4347157 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5484. Min Range: -3.5484
Max Act: 3.3290. Min Act: -0.1700
Data Index: 7471244 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5484. Min Range: -3.5484
Max Act: 3.2976. Min Act: -0.1700
Data Index: 8037345 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5484. Min Range: -3.5484
Max Act: 3.2976. Min Act: -0.1700
Data Index: 3515200 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5484. Min Range: -3.5484
Max Act: 3.3133. Min Act: -0.1700
Data Index: 8474774 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5484. Min Range: -3.5484
Max Act: 3.3133. Min Act: -0.1700
Data Index: 373925 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5484. Min Range: -3.5484
Max Act: 3.2976. Min Act: -0.1700
Data Index: 5852023 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5484. Min Range: -3.5484
Max Act: 3.2819. Min Act: -0.1700
Data Index: 8159162 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5484. Min Range: -3.5484
Max Act: 3.2662. Min Act: -0.1700
Data Index: 4861090 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19