Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3555 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5729. Min Range: -4.5729
Max Act: 4.5729. Min Act: -0.1700
Data Index: 735761 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5729. Min Range: -4.5729
Max Act: 4.5729. Min Act: -0.1700
Data Index: 5261324 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5729. Min Range: -4.5729
Max Act: 4.5104. Min Act: -0.1700
Data Index: 670806 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5729. Min Range: -4.5729
Max Act: 4.5104. Min Act: -0.1700
Data Index: 7888616 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5729. Min Range: -4.5729
Max Act: 4.5104. Min Act: -0.1700
Data Index: 7934595 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5729. Min Range: -4.5729
Max Act: 4.5104. Min Act: -0.1700
Data Index: 4760791 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5729. Min Range: -4.5729
Max Act: 4.5104. Min Act: -0.1700
Data Index: 5894447 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5729. Min Range: -4.5729
Max Act: 4.4792. Min Act: -0.1700
Data Index: 5292383 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5729. Min Range: -4.5729
Max Act: 4.4479. Min Act: -0.1700
Data Index: 76324 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5729. Min Range: -4.5729
Max Act: 4.4167. Min Act: -0.1700
Data Index: 196325 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5729. Min Range: -4.5729
Max Act: 4.4479. Min Act: -0.1700
Data Index: 4650618 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5729. Min Range: -4.5729
Max Act: 4.4479. Min Act: -0.1700
Data Index: 7245703 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5729. Min Range: -4.5729
Max Act: 4.4167. Min Act: -0.1700
Data Index: 5116961 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5729. Min Range: -4.5729
Max Act: 4.4167. Min Act: -0.1700
Data Index: 8547113 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5729. Min Range: -4.5729
Max Act: 4.4167. Min Act: -0.1700
Data Index: 4619372 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5729. Min Range: -4.5729
Max Act: 4.3854. Min Act: -0.1700
Data Index: 5377588 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5729. Min Range: -4.5729
Max Act: 4.4167. Min Act: -0.1700
Data Index: 5569206 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5729. Min Range: -4.5729
Max Act: 4.3854. Min Act: -0.1700
Data Index: 2209236 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5729. Min Range: -4.5729
Max Act: 4.3854. Min Act: -0.1700
Data Index: 7666063 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5729. Min Range: -4.5729
Max Act: 4.3854. Min Act: -0.1700
Data Index: 1535301 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19