Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3782 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.8431. Min Act: -0.1700
Data Index: 6163540 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.7494. Min Act: -0.1700
Data Index: 4965338 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.6556. Min Act: -0.1700
Data Index: 8585936 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.6244. Min Act: -0.1700
Data Index: 767847 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.6244. Min Act: -0.1700
Data Index: 2040822 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.5931. Min Act: -0.1700
Data Index: 3894920 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.6244. Min Act: -0.1700
Data Index: 583447 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.5931. Min Act: -0.1700
Data Index: 6619837 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.5619. Min Act: -0.1700
Data Index: 4350775 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.5306. Min Act: -0.1700
Data Index: 7004642 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.4994. Min Act: -0.1700
Data Index: 7794348 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.4994. Min Act: -0.1700
Data Index: 3527689 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.4369. Min Act: -0.1700
Data Index: 6997484 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.4681. Min Act: -0.1700
Data Index: 3920142 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.4369. Min Act: -0.1700
Data Index: 1245610 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.4056. Min Act: -0.1700
Data Index: 8759795 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.4056. Min Act: -0.1700
Data Index: 8071073 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.4056. Min Act: -0.1700
Data Index: 1543368 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.3744. Min Act: -0.1700
Data Index: 7751458 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8431. Min Range: -6.8431
Max Act: 6.3431. Min Act: -0.1700
Data Index: 2579503 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19