Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4035 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7823. Min Range: -7.7823
Max Act: 7.7823. Min Act: -0.1700
Data Index: 1424370 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7823. Min Range: -7.7823
Max Act: 7.6885. Min Act: -0.1700
Data Index: 3879105 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7823. Min Range: -7.7823
Max Act: 7.5948. Min Act: -0.1700
Data Index: 120743 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7823. Min Range: -7.7823
Max Act: 7.5010. Min Act: -0.1700
Data Index: 3055579 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7823. Min Range: -7.7823
Max Act: 7.4073. Min Act: -0.1700
Data Index: 8098831 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7823. Min Range: -7.7823
Max Act: 7.4385. Min Act: -0.1700
Data Index: 111762 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7823. Min Range: -7.7823
Max Act: 7.4073. Min Act: -0.1700
Data Index: 749784 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7823. Min Range: -7.7823
Max Act: 7.4073. Min Act: -0.1700
Data Index: 3827181 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7823. Min Range: -7.7823
Max Act: 7.3448. Min Act: -0.1700
Data Index: 4276548 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7823. Min Range: -7.7823
Max Act: 7.3760. Min Act: -0.1700
Data Index: 2657252 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7823. Min Range: -7.7823
Max Act: 7.3448. Min Act: -0.1700
Data Index: 5146287 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7823. Min Range: -7.7823
Max Act: 7.3448. Min Act: -0.1700
Data Index: 4978763 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7823. Min Range: -7.7823
Max Act: 7.3135. Min Act: -0.1700
Data Index: 6483380 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7823. Min Range: -7.7823
Max Act: 7.3448. Min Act: -0.1700
Data Index: 4761023 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7823. Min Range: -7.7823
Max Act: 7.3135. Min Act: -0.1700
Data Index: 3647483 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7823. Min Range: -7.7823
Max Act: 7.3135. Min Act: -0.1700
Data Index: 7089828 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7823. Min Range: -7.7823
Max Act: 7.3135. Min Act: -0.1700
Data Index: 7081282 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7823. Min Range: -7.7823
Max Act: 7.3135. Min Act: -0.1700
Data Index: 4735509 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7823. Min Range: -7.7823
Max Act: 7.3448. Min Act: -0.1700
Data Index: 1744782 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7823. Min Range: -7.7823
Max Act: 7.2823. Min Act: -0.1700
Data Index: 6245797 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19