Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3740. Min Range: -5.3740
Max Act: 5.3740. Min Act: -0.1700
Data Index: 7966798 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3740. Min Range: -5.3740
Max Act: 5.3740. Min Act: -0.1700
Data Index: 2857186 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3740. Min Range: -5.3740
Max Act: 5.3428. Min Act: -0.1700
Data Index: 5884186 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3740. Min Range: -5.3740
Max Act: 5.3115. Min Act: -0.1700
Data Index: 3514482 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3740. Min Range: -5.3740
Max Act: 5.3115. Min Act: -0.1700
Data Index: 1194542 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3740. Min Range: -5.3740
Max Act: 5.3115. Min Act: -0.1700
Data Index: 2416997 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3740. Min Range: -5.3740
Max Act: 5.3115. Min Act: -0.1700
Data Index: 1828998 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3740. Min Range: -5.3740
Max Act: 5.3115. Min Act: -0.1700
Data Index: 4769350 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3740. Min Range: -5.3740
Max Act: 5.3115. Min Act: -0.1700
Data Index: 6777846 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3740. Min Range: -5.3740
Max Act: 5.3115. Min Act: -0.1700
Data Index: 1731445 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3740. Min Range: -5.3740
Max Act: 5.3115. Min Act: -0.1700
Data Index: 4675569 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3740. Min Range: -5.3740
Max Act: 5.3115. Min Act: -0.1700
Data Index: 2771503 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3740. Min Range: -5.3740
Max Act: 5.2803. Min Act: -0.1700
Data Index: 4211517 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3740. Min Range: -5.3740
Max Act: 5.2803. Min Act: -0.1700
Data Index: 3281832 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3740. Min Range: -5.3740
Max Act: 5.2803. Min Act: -0.1700
Data Index: 2666662 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3740. Min Range: -5.3740
Max Act: 5.2803. Min Act: -0.1700
Data Index: 6922188 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3740. Min Range: -5.3740
Max Act: 5.2803. Min Act: -0.1700
Data Index: 5782822 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3740. Min Range: -5.3740
Max Act: 5.2803. Min Act: -0.1700
Data Index: 8016274 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3740. Min Range: -5.3740
Max Act: 5.2803. Min Act: -0.1700
Data Index: 5545698 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3740. Min Range: -5.3740
Max Act: 5.2803. Min Act: -0.1700
Data Index: 8804870 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19