Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3822 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4004. Min Range: -6.4004
Max Act: 6.4004. Min Act: -0.1700
Data Index: 1319716 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4004. Min Range: -6.4004
Max Act: 6.3692. Min Act: -0.1700
Data Index: 4989924 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4004. Min Range: -6.4004
Max Act: 6.3067. Min Act: -0.1700
Data Index: 5941404 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4004. Min Range: -6.4004
Max Act: 6.3067. Min Act: -0.1700
Data Index: 4166193 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4004. Min Range: -6.4004
Max Act: 6.2129. Min Act: -0.1700
Data Index: 2408512 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4004. Min Range: -6.4004
Max Act: 6.1504. Min Act: -0.1700
Data Index: 5778391 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4004. Min Range: -6.4004
Max Act: 6.1817. Min Act: -0.1700
Data Index: 4706832 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4004. Min Range: -6.4004
Max Act: 6.1504. Min Act: -0.1700
Data Index: 7481260 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4004. Min Range: -6.4004
Max Act: 6.1504. Min Act: -0.1700
Data Index: 6460333 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4004. Min Range: -6.4004
Max Act: 6.1192. Min Act: -0.1700
Data Index: 33243 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4004. Min Range: -6.4004
Max Act: 6.1192. Min Act: -0.1700
Data Index: 5236276 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4004. Min Range: -6.4004
Max Act: 6.1192. Min Act: -0.1700
Data Index: 5045247 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4004. Min Range: -6.4004
Max Act: 6.1192. Min Act: -0.1700
Data Index: 2711857 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4004. Min Range: -6.4004
Max Act: 6.1192. Min Act: -0.1700
Data Index: 3972740 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4004. Min Range: -6.4004
Max Act: 6.1192. Min Act: -0.1700
Data Index: 6749705 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4004. Min Range: -6.4004
Max Act: 6.1192. Min Act: -0.1700
Data Index: 6411649 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4004. Min Range: -6.4004
Max Act: 6.0567. Min Act: -0.1700
Data Index: 1653749 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4004. Min Range: -6.4004
Max Act: 6.0879. Min Act: -0.1699
Data Index: 506701 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4004. Min Range: -6.4004
Max Act: 6.0567. Min Act: -0.1700
Data Index: 6529785 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4004. Min Range: -6.4004
Max Act: 6.0879. Min Act: -0.1700
Data Index: 5526686 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19