Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6240 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8398. Min Range: -4.8398
Max Act: 4.8398. Min Act: -0.1700
Data Index: 3044241 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8398. Min Range: -4.8398
Max Act: 4.8085. Min Act: -0.1700
Data Index: 8461815 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8398. Min Range: -4.8398
Max Act: 4.7460. Min Act: -0.1700
Data Index: 4950191 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8398. Min Range: -4.8398
Max Act: 4.6835. Min Act: -0.1700
Data Index: 283342 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8398. Min Range: -4.8398
Max Act: 4.6523. Min Act: -0.1700
Data Index: 6630152 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8398. Min Range: -4.8398
Max Act: 4.6523. Min Act: -0.1700
Data Index: 6497563 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8398. Min Range: -4.8398
Max Act: 4.6210. Min Act: -0.1700
Data Index: 122883 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8398. Min Range: -4.8398
Max Act: 4.6523. Min Act: -0.1700
Data Index: 2282980 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8398. Min Range: -4.8398
Max Act: 4.6210. Min Act: -0.1700
Data Index: 8635717 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8398. Min Range: -4.8398
Max Act: 4.5898. Min Act: -0.1700
Data Index: 653999 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8398. Min Range: -4.8398
Max Act: 4.6210. Min Act: -0.1700
Data Index: 5165682 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8398. Min Range: -4.8398
Max Act: 4.5898. Min Act: -0.1700
Data Index: 7513164 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8398. Min Range: -4.8398
Max Act: 4.5898. Min Act: -0.1700
Data Index: 382410 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8398. Min Range: -4.8398
Max Act: 4.5585. Min Act: -0.1700
Data Index: 3035778 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8398. Min Range: -4.8398
Max Act: 4.5585. Min Act: -0.1700
Data Index: 6608033 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8398. Min Range: -4.8398
Max Act: 4.5273. Min Act: -0.1700
Data Index: 6374089 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8398. Min Range: -4.8398
Max Act: 4.5585. Min Act: -0.1700
Data Index: 2328598 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8398. Min Range: -4.8398
Max Act: 4.5585. Min Act: -0.1700
Data Index: 3969354 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8398. Min Range: -4.8398
Max Act: 4.5585. Min Act: -0.1700
Data Index: 7528109 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8398. Min Range: -4.8398
Max Act: 4.5273. Min Act: -0.1700
Data Index: 6684832 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19