Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3198 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7883. Min Range: -5.7883
Max Act: 5.7883. Min Act: -0.1700
Data Index: 7375594 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7883. Min Range: -5.7883
Max Act: 5.6946. Min Act: -0.1700
Data Index: 1542429 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7883. Min Range: -5.7883
Max Act: 5.6321. Min Act: -0.1700
Data Index: 8544786 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7883. Min Range: -5.7883
Max Act: 5.5383. Min Act: -0.1700
Data Index: 4498214 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7883. Min Range: -5.7883
Max Act: 5.4758. Min Act: -0.1700
Data Index: 4424303 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7883. Min Range: -5.7883
Max Act: 5.4446. Min Act: -0.1700
Data Index: 8086605 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7883. Min Range: -5.7883
Max Act: 5.4446. Min Act: -0.1700
Data Index: 7271960 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7883. Min Range: -5.7883
Max Act: 5.4133. Min Act: -0.1700
Data Index: 1490718 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7883. Min Range: -5.7883
Max Act: 5.3196. Min Act: -0.1700
Data Index: 8544794 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7883. Min Range: -5.7883
Max Act: 5.3508. Min Act: -0.1700
Data Index: 6518684 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7883. Min Range: -5.7883
Max Act: 5.3508. Min Act: -0.1700
Data Index: 3781277 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7883. Min Range: -5.7883
Max Act: 5.3196. Min Act: -0.1700
Data Index: 377795 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7883. Min Range: -5.7883
Max Act: 5.3196. Min Act: -0.1700
Data Index: 764733 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7883. Min Range: -5.7883
Max Act: 5.3196. Min Act: -0.1700
Data Index: 5417229 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7883. Min Range: -5.7883
Max Act: 5.3196. Min Act: -0.1700
Data Index: 8618548 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7883. Min Range: -5.7883
Max Act: 5.2883. Min Act: -0.1700
Data Index: 724200 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7883. Min Range: -5.7883
Max Act: 5.2571. Min Act: -0.1700
Data Index: 6906457 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7883. Min Range: -5.7883
Max Act: 5.2571. Min Act: -0.1700
Data Index: 4545794 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7883. Min Range: -5.7883
Max Act: 5.2258. Min Act: -0.1700
Data Index: 8782379 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7883. Min Range: -5.7883
Max Act: 5.2258. Min Act: -0.1700
Data Index: 7955642 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19