Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7565. Min Range: -6.7565
Max Act: 6.7565. Min Act: -0.1700
Data Index: 2095466 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7565. Min Range: -6.7565
Max Act: 6.5378. Min Act: -0.1700
Data Index: 3980248 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7565. Min Range: -6.7565
Max Act: 6.4753. Min Act: -0.1700
Data Index: 8658150 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7565. Min Range: -6.7565
Max Act: 6.4440. Min Act: -0.1700
Data Index: 3431103 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7565. Min Range: -6.7565
Max Act: 6.5065. Min Act: -0.1700
Data Index: 2963953 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7565. Min Range: -6.7565
Max Act: 6.4440. Min Act: -0.1700
Data Index: 245207 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7565. Min Range: -6.7565
Max Act: 6.4440. Min Act: -0.1700
Data Index: 1146571 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7565. Min Range: -6.7565
Max Act: 6.3815. Min Act: -0.1700
Data Index: 174960 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7565. Min Range: -6.7565
Max Act: 6.4128. Min Act: -0.1700
Data Index: 7315333 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7565. Min Range: -6.7565
Max Act: 6.3503. Min Act: -0.1700
Data Index: 3331696 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7565. Min Range: -6.7565
Max Act: 6.3190. Min Act: -0.1700
Data Index: 7555384 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7565. Min Range: -6.7565
Max Act: 6.3190. Min Act: -0.1700
Data Index: 4500692 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7565. Min Range: -6.7565
Max Act: 6.2878. Min Act: -0.1700
Data Index: 1053349 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7565. Min Range: -6.7565
Max Act: 6.2878. Min Act: -0.1700
Data Index: 5422303 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7565. Min Range: -6.7565
Max Act: 6.3190. Min Act: -0.1700
Data Index: 6099247 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7565. Min Range: -6.7565
Max Act: 6.2878. Min Act: -0.1700
Data Index: 4255160 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7565. Min Range: -6.7565
Max Act: 6.2565. Min Act: -0.1700
Data Index: 5210264 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7565. Min Range: -6.7565
Max Act: 6.2565. Min Act: -0.1700
Data Index: 566070 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7565. Min Range: -6.7565
Max Act: 6.2253. Min Act: -0.1700
Data Index: 2643523 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7565. Min Range: -6.7565
Max Act: 6.2253. Min Act: -0.1700
Data Index: 1380027 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19