Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2928 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6735. Min Range: -8.6735
Max Act: 8.6735. Min Act: -0.1700
Data Index: 2293010 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6735. Min Range: -8.6735
Max Act: 8.5485. Min Act: -0.1700
Data Index: 3955295 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6735. Min Range: -8.6735
Max Act: 8.5485. Min Act: -0.1700
Data Index: 6603935 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6735. Min Range: -8.6735
Max Act: 8.2360. Min Act: -0.1700
Data Index: 3348020 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6735. Min Range: -8.6735
Max Act: 8.1735. Min Act: -0.1700
Data Index: 7824827 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6735. Min Range: -8.6735
Max Act: 8.0485. Min Act: -0.1700
Data Index: 2876776 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6735. Min Range: -8.6735
Max Act: 8.1110. Min Act: -0.1700
Data Index: 3004816 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6735. Min Range: -8.6735
Max Act: 7.9860. Min Act: -0.1700
Data Index: 1855262 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6735. Min Range: -8.6735
Max Act: 8.0485. Min Act: -0.1700
Data Index: 8169833 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6735. Min Range: -8.6735
Max Act: 8.0485. Min Act: -0.1700
Data Index: 1626490 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6735. Min Range: -8.6735
Max Act: 8.0485. Min Act: -0.1700
Data Index: 4354437 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6735. Min Range: -8.6735
Max Act: 7.9860. Min Act: -0.1700
Data Index: 2944185 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6735. Min Range: -8.6735
Max Act: 7.9860. Min Act: -0.1700
Data Index: 5198524 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6735. Min Range: -8.6735
Max Act: 8.0485. Min Act: -0.1700
Data Index: 8494725 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6735. Min Range: -8.6735
Max Act: 7.9860. Min Act: -0.1700
Data Index: 4774586 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6735. Min Range: -8.6735
Max Act: 7.9860. Min Act: -0.1700
Data Index: 6271375 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6735. Min Range: -8.6735
Max Act: 7.9860. Min Act: -0.1700
Data Index: 3327781 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6735. Min Range: -8.6735
Max Act: 7.9860. Min Act: -0.1700
Data Index: 4613049 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6735. Min Range: -8.6735
Max Act: 7.9860. Min Act: -0.1700
Data Index: 1368022 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6735. Min Range: -8.6735
Max Act: 8.0485. Min Act: -0.1700
Data Index: 4073416 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19