Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.6362. Min Act: -0.1700
Data Index: 186770 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.5266. Min Act: -0.1700
Data Index: 2533495 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.4013. Min Act: -0.1700
Data Index: 4712799 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.3543. Min Act: -0.1700
Data Index: 8025279 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.3699. Min Act: -0.1700
Data Index: 7593566 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.3543. Min Act: -0.1700
Data Index: 8025085 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.3699. Min Act: -0.1700
Data Index: 6608357 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.3229. Min Act: -0.1700
Data Index: 5950636 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.3229. Min Act: -0.1700
Data Index: 2817984 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.3229. Min Act: -0.1700
Data Index: 4775554 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.3229. Min Act: -0.1700
Data Index: 1619233 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.3386. Min Act: -0.1700
Data Index: 2894482 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.3072. Min Act: -0.1700
Data Index: 8381507 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.3072. Min Act: -0.1700
Data Index: 2182367 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.3072. Min Act: -0.1700
Data Index: 4397722 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.3072. Min Act: -0.1700
Data Index: 6365377 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.2758. Min Act: -0.1700
Data Index: 2064382 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.3072. Min Act: -0.1700
Data Index: 8048835 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.2758. Min Act: -0.1700
Data Index: 1573717 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.2758. Min Act: -0.1700
Data Index: 4516646 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19