Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4630 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1200. Min Range: -5.1200
Max Act: 5.1200. Min Act: -0.1700
Data Index: 7859158 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.9013. Min Act: -0.1700
Data Index: 3605407 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.8075. Min Act: -0.1700
Data Index: 2533689 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.8388. Min Act: -0.1700
Data Index: 7061603 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.8388. Min Act: -0.1700
Data Index: 52991 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.7450. Min Act: -0.1700
Data Index: 3574479 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.7450. Min Act: -0.1700
Data Index: 4384566 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.7450. Min Act: -0.1700
Data Index: 8651967 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.7138. Min Act: -0.1700
Data Index: 2061420 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.7138. Min Act: -0.1700
Data Index: 1336526 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.7138. Min Act: -0.1700
Data Index: 7303355 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.7138. Min Act: -0.1700
Data Index: 1018743 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.6825. Min Act: -0.1700
Data Index: 4972316 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.6513. Min Act: -0.1700
Data Index: 5389881 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.6513. Min Act: -0.1700
Data Index: 8350412 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.6513. Min Act: -0.1700
Data Index: 4967975 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.6825. Min Act: -0.1700
Data Index: 2298258 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.6513. Min Act: -0.1700
Data Index: 3277619 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.6513. Min Act: -0.1700
Data Index: 4352412 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.6200. Min Act: -0.1700
Data Index: 3071565 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19