Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2057 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7537. Min Range: -3.7537
Max Act: 3.7537. Min Act: -0.1700
Data Index: 1455035 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7537. Min Range: -3.7537
Max Act: 3.6286. Min Act: -0.1700
Data Index: 494710 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7537. Min Range: -3.7537
Max Act: 3.5503. Min Act: -0.1700
Data Index: 327895 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7537. Min Range: -3.7537
Max Act: 3.5190. Min Act: -0.1700
Data Index: 1184200 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7537. Min Range: -3.7537
Max Act: 3.5033. Min Act: -0.1700
Data Index: 5899509 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7537. Min Range: -3.7537
Max Act: 3.5190. Min Act: -0.1700
Data Index: 3688760 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7537. Min Range: -3.7537
Max Act: 3.5033. Min Act: -0.1700
Data Index: 7168309 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7537. Min Range: -3.7537
Max Act: 3.4720. Min Act: -0.1700
Data Index: 1857832 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7537. Min Range: -3.7537
Max Act: 3.4720. Min Act: -0.1700
Data Index: 1449342 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7537. Min Range: -3.7537
Max Act: 3.4563. Min Act: -0.1700
Data Index: 647552 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7537. Min Range: -3.7537
Max Act: 3.4407. Min Act: -0.1700
Data Index: 4661526 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7537. Min Range: -3.7537
Max Act: 3.4250. Min Act: -0.1700
Data Index: 3576329 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7537. Min Range: -3.7537
Max Act: 3.4250. Min Act: -0.1700
Data Index: 3300653 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7537. Min Range: -3.7537
Max Act: 3.3623. Min Act: -0.1700
Data Index: 8711296 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7537. Min Range: -3.7537
Max Act: 3.3623. Min Act: -0.1700
Data Index: 1407549 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7537. Min Range: -3.7537
Max Act: 3.3466. Min Act: -0.1700
Data Index: 2745391 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7537. Min Range: -3.7537
Max Act: 3.3466. Min Act: -0.1700
Data Index: 2688577 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7537. Min Range: -3.7537
Max Act: 3.3466. Min Act: -0.1700
Data Index: 7789829 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7537. Min Range: -3.7537
Max Act: 3.3466. Min Act: -0.1700
Data Index: 4977402 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7537. Min Range: -3.7537
Max Act: 3.3309. Min Act: -0.1700
Data Index: 2120626 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19