Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9286. Min Range: -5.9286
Max Act: 5.9286. Min Act: -0.1700
Data Index: 5449222 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9286. Min Range: -5.9286
Max Act: 5.9286. Min Act: -0.1700
Data Index: 7917321 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9286. Min Range: -5.9286
Max Act: 5.8973. Min Act: -0.1700
Data Index: 5479181 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9286. Min Range: -5.9286
Max Act: 5.8036. Min Act: -0.1700
Data Index: 6969256 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9286. Min Range: -5.9286
Max Act: 5.7411. Min Act: -0.1700
Data Index: 7001015 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9286. Min Range: -5.9286
Max Act: 5.7411. Min Act: -0.1700
Data Index: 7045026 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9286. Min Range: -5.9286
Max Act: 5.7098. Min Act: -0.1700
Data Index: 5434707 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9286. Min Range: -5.9286
Max Act: 5.6786. Min Act: -0.1700
Data Index: 8614228 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9286. Min Range: -5.9286
Max Act: 5.6786. Min Act: -0.1700
Data Index: 4979289 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9286. Min Range: -5.9286
Max Act: 5.6473. Min Act: -0.1700
Data Index: 1567477 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9286. Min Range: -5.9286
Max Act: 5.5848. Min Act: -0.1700
Data Index: 7922608 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9286. Min Range: -5.9286
Max Act: 5.5848. Min Act: -0.1700
Data Index: 7317278 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9286. Min Range: -5.9286
Max Act: 5.5848. Min Act: -0.1700
Data Index: 2790870 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9286. Min Range: -5.9286
Max Act: 5.5848. Min Act: -0.1700
Data Index: 269951 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9286. Min Range: -5.9286
Max Act: 5.5536. Min Act: -0.1700
Data Index: 4551070 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9286. Min Range: -5.9286
Max Act: 5.5536. Min Act: -0.1700
Data Index: 6047827 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9286. Min Range: -5.9286
Max Act: 5.5536. Min Act: -0.1700
Data Index: 8320577 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9286. Min Range: -5.9286
Max Act: 5.5536. Min Act: -0.1700
Data Index: 1287546 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9286. Min Range: -5.9286
Max Act: 5.5536. Min Act: -0.1700
Data Index: 1533939 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9286. Min Range: -5.9286
Max Act: 5.5536. Min Act: -0.1700
Data Index: 1057719 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19