Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6055 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9823. Min Range: -6.9823
Max Act: 6.9823. Min Act: -0.1700
Data Index: 2020073 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9823. Min Range: -6.9823
Max Act: 6.9198. Min Act: -0.1700
Data Index: 6731942 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9823. Min Range: -6.9823
Max Act: 6.7948. Min Act: -0.1700
Data Index: 4397802 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9823. Min Range: -6.9823
Max Act: 6.7323. Min Act: -0.1700
Data Index: 1198336 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9823. Min Range: -6.9823
Max Act: 6.7323. Min Act: -0.1700
Data Index: 2363976 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9823. Min Range: -6.9823
Max Act: 6.7010. Min Act: -0.1700
Data Index: 8224646 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9823. Min Range: -6.9823
Max Act: 6.7010. Min Act: -0.1700
Data Index: 5477376 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9823. Min Range: -6.9823
Max Act: 6.6385. Min Act: -0.1700
Data Index: 5569618 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9823. Min Range: -6.9823
Max Act: 6.6385. Min Act: -0.1700
Data Index: 3940062 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9823. Min Range: -6.9823
Max Act: 6.5760. Min Act: -0.1700
Data Index: 332702 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9823. Min Range: -6.9823
Max Act: 6.5448. Min Act: -0.1700
Data Index: 7443064 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9823. Min Range: -6.9823
Max Act: 6.5448. Min Act: -0.1700
Data Index: 2189313 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9823. Min Range: -6.9823
Max Act: 6.5760. Min Act: -0.1700
Data Index: 3128754 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9823. Min Range: -6.9823
Max Act: 6.5135. Min Act: -0.1700
Data Index: 5738986 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9823. Min Range: -6.9823
Max Act: 6.5135. Min Act: -0.1700
Data Index: 3217612 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9823. Min Range: -6.9823
Max Act: 6.5135. Min Act: -0.1700
Data Index: 7816495 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9823. Min Range: -6.9823
Max Act: 6.4823. Min Act: -0.1700
Data Index: 17561 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9823. Min Range: -6.9823
Max Act: 6.4823. Min Act: -0.1700
Data Index: 1996558 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9823. Min Range: -6.9823
Max Act: 6.4510. Min Act: -0.1700
Data Index: 5022673 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9823. Min Range: -6.9823
Max Act: 6.4510. Min Act: -0.1700
Data Index: 4621789 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19