Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2433 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4268. Min Range: -6.4268
Max Act: 6.4268. Min Act: -0.1700
Data Index: 6652727 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4268. Min Range: -6.4268
Max Act: 6.2393. Min Act: -0.1700
Data Index: 1626107 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4268. Min Range: -6.4268
Max Act: 6.2705. Min Act: -0.1700
Data Index: 3446511 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4268. Min Range: -6.4268
Max Act: 6.2080. Min Act: -0.1700
Data Index: 6487470 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4268. Min Range: -6.4268
Max Act: 6.1768. Min Act: -0.1700
Data Index: 7458813 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4268. Min Range: -6.4268
Max Act: 6.1143. Min Act: -0.1700
Data Index: 4608038 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4268. Min Range: -6.4268
Max Act: 6.1143. Min Act: -0.1700
Data Index: 2251364 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4268. Min Range: -6.4268
Max Act: 6.0830. Min Act: -0.1700
Data Index: 7382565 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4268. Min Range: -6.4268
Max Act: 6.0205. Min Act: -0.1700
Data Index: 402517 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4268. Min Range: -6.4268
Max Act: 6.0205. Min Act: -0.1700
Data Index: 5887340 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4268. Min Range: -6.4268
Max Act: 5.9893. Min Act: -0.1700
Data Index: 5851290 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4268. Min Range: -6.4268
Max Act: 5.9268. Min Act: -0.1700
Data Index: 1844936 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4268. Min Range: -6.4268
Max Act: 5.9580. Min Act: -0.1700
Data Index: 75957 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4268. Min Range: -6.4268
Max Act: 5.9580. Min Act: -0.1700
Data Index: 2818948 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4268. Min Range: -6.4268
Max Act: 5.9893. Min Act: -0.1700
Data Index: 6285933 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4268. Min Range: -6.4268
Max Act: 5.9268. Min Act: -0.1700
Data Index: 1965808 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4268. Min Range: -6.4268
Max Act: 5.9268. Min Act: -0.1700
Data Index: 7207792 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4268. Min Range: -6.4268
Max Act: 5.9268. Min Act: -0.1700
Data Index: 7219628 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4268. Min Range: -6.4268
Max Act: 5.9268. Min Act: -0.1700
Data Index: 4891356 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4268. Min Range: -6.4268
Max Act: 5.8643. Min Act: -0.1700
Data Index: 7349918 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19