Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3196 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.7461. Min Act: -0.1700
Data Index: 4850514 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.6836. Min Act: -0.1700
Data Index: 6807467 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.5899. Min Act: -0.1700
Data Index: 2875078 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.6211. Min Act: -0.1700
Data Index: 4166274 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.5586. Min Act: -0.1700
Data Index: 6780885 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.4961. Min Act: -0.1700
Data Index: 4597992 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.4336. Min Act: -0.1700
Data Index: 5826974 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.4649. Min Act: -0.1700
Data Index: 5067029 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.4024. Min Act: -0.1700
Data Index: 8805928 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.4024. Min Act: -0.1700
Data Index: 2477874 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.3399. Min Act: -0.1700
Data Index: 5207404 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.3711. Min Act: -0.1700
Data Index: 8501290 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.2774. Min Act: -0.1700
Data Index: 4583846 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.2774. Min Act: -0.1700
Data Index: 8094079 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.2149. Min Act: -0.1700
Data Index: 925394 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.2149. Min Act: -0.1700
Data Index: 212843 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.1836. Min Act: -0.1700
Data Index: 4081226 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.2461. Min Act: -0.1700
Data Index: 5159047 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.1836. Min Act: -0.1700
Data Index: 1231280 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.1836. Min Act: -0.1700
Data Index: 7694422 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19