Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7466. Min Range: -3.7466
Max Act: 3.7466. Min Act: -0.1700
Data Index: 7694107 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7466. Min Range: -3.7466
Max Act: 3.6840. Min Act: -0.1700
Data Index: 8228247 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7466. Min Range: -3.7466
Max Act: 3.5901. Min Act: -0.1700
Data Index: 8431884 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7466. Min Range: -3.7466
Max Act: 3.5901. Min Act: -0.1700
Data Index: 5816656 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7466. Min Range: -3.7466
Max Act: 3.5588. Min Act: -0.1700
Data Index: 1645923 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7466. Min Range: -3.7466
Max Act: 3.5901. Min Act: -0.1700
Data Index: 5369651 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7466. Min Range: -3.7466
Max Act: 3.5588. Min Act: -0.1700
Data Index: 8571780 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7466. Min Range: -3.7466
Max Act: 3.5275. Min Act: -0.1700
Data Index: 343102 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7466. Min Range: -3.7466
Max Act: 3.5275. Min Act: -0.1700
Data Index: 7185353 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7466. Min Range: -3.7466
Max Act: 3.5275. Min Act: -0.1700
Data Index: 1972455 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7466. Min Range: -3.7466
Max Act: 3.5275. Min Act: -0.1700
Data Index: 1941164 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7466. Min Range: -3.7466
Max Act: 3.4962. Min Act: -0.1700
Data Index: 8712361 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7466. Min Range: -3.7466
Max Act: 3.5275. Min Act: -0.1700
Data Index: 5571373 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7466. Min Range: -3.7466
Max Act: 3.4649. Min Act: -0.1700
Data Index: 8720139 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7466. Min Range: -3.7466
Max Act: 3.4962. Min Act: -0.1700
Data Index: 8046658 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7466. Min Range: -3.7466
Max Act: 3.4962. Min Act: -0.1700
Data Index: 2289207 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7466. Min Range: -3.7466
Max Act: 3.4649. Min Act: -0.1700
Data Index: 5910770 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7466. Min Range: -3.7466
Max Act: 3.4649. Min Act: -0.1700
Data Index: 1737606 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7466. Min Range: -3.7466
Max Act: 3.4492. Min Act: -0.1700
Data Index: 2367701 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7466. Min Range: -3.7466
Max Act: 3.4492. Min Act: -0.1700
Data Index: 776540 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19