Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6142 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5947. Min Range: -5.5947
Max Act: 5.5947. Min Act: -0.1700
Data Index: 3416163 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5947. Min Range: -5.5947
Max Act: 5.4072. Min Act: -0.1700
Data Index: 2316629 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5947. Min Range: -5.5947
Max Act: 5.4072. Min Act: -0.1700
Data Index: 4422961 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5947. Min Range: -5.5947
Max Act: 5.3760. Min Act: -0.1700
Data Index: 1998162 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5947. Min Range: -5.5947
Max Act: 5.3447. Min Act: -0.1700
Data Index: 8280190 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5947. Min Range: -5.5947
Max Act: 5.3135. Min Act: -0.1700
Data Index: 991461 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5947. Min Range: -5.5947
Max Act: 5.3135. Min Act: -0.1700
Data Index: 2316630 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5947. Min Range: -5.5947
Max Act: 5.3135. Min Act: -0.1700
Data Index: 1998145 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5947. Min Range: -5.5947
Max Act: 5.2822. Min Act: -0.1700
Data Index: 6021093 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5947. Min Range: -5.5947
Max Act: 5.2822. Min Act: -0.1700
Data Index: 3416164 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5947. Min Range: -5.5947
Max Act: 5.2197. Min Act: -0.1700
Data Index: 1999294 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5947. Min Range: -5.5947
Max Act: 5.2197. Min Act: -0.1700
Data Index: 1741435 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5947. Min Range: -5.5947
Max Act: 5.1885. Min Act: -0.1700
Data Index: 528692 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5947. Min Range: -5.5947
Max Act: 5.1885. Min Act: -0.1700
Data Index: 4462199 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5947. Min Range: -5.5947
Max Act: 5.1885. Min Act: -0.1700
Data Index: 182730 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5947. Min Range: -5.5947
Max Act: 5.1885. Min Act: -0.1700
Data Index: 1774038 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5947. Min Range: -5.5947
Max Act: 5.1572. Min Act: -0.1700
Data Index: 2860545 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5947. Min Range: -5.5947
Max Act: 5.1572. Min Act: -0.1700
Data Index: 818240 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5947. Min Range: -5.5947
Max Act: 5.1572. Min Act: -0.1700
Data Index: 5815259 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5947. Min Range: -5.5947
Max Act: 5.1260. Min Act: -0.1700
Data Index: 5404306 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19