Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3197 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7552. Min Range: -5.7552
Max Act: 5.7240. Min Act: -0.1700
Data Index: 295524 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7552. Min Range: -5.7552
Max Act: 5.7552. Min Act: -0.1700
Data Index: 1419468 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7552. Min Range: -5.7552
Max Act: 5.7240. Min Act: -0.1700
Data Index: 4025785 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7552. Min Range: -5.7552
Max Act: 5.6615. Min Act: -0.1700
Data Index: 2325633 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7552. Min Range: -5.7552
Max Act: 5.5990. Min Act: -0.1700
Data Index: 7298036 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7552. Min Range: -5.7552
Max Act: 5.5990. Min Act: -0.1700
Data Index: 7993382 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7552. Min Range: -5.7552
Max Act: 5.5677. Min Act: -0.1700
Data Index: 4962906 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7552. Min Range: -5.7552
Max Act: 5.5677. Min Act: -0.1700
Data Index: 241174 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7552. Min Range: -5.7552
Max Act: 5.5365. Min Act: -0.1700
Data Index: 1880794 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7552. Min Range: -5.7552
Max Act: 5.5052. Min Act: -0.1700
Data Index: 6774341 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7552. Min Range: -5.7552
Max Act: 5.5052. Min Act: -0.1700
Data Index: 2145393 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7552. Min Range: -5.7552
Max Act: 5.4427. Min Act: -0.1700
Data Index: 181882 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7552. Min Range: -5.7552
Max Act: 5.4740. Min Act: -0.1700
Data Index: 2278707 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7552. Min Range: -5.7552
Max Act: 5.4740. Min Act: -0.1700
Data Index: 8483108 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7552. Min Range: -5.7552
Max Act: 5.4740. Min Act: -0.1700
Data Index: 2582007 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7552. Min Range: -5.7552
Max Act: 5.4115. Min Act: -0.1700
Data Index: 5389071 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7552. Min Range: -5.7552
Max Act: 5.4427. Min Act: -0.1700
Data Index: 6617191 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7552. Min Range: -5.7552
Max Act: 5.4427. Min Act: -0.1700
Data Index: 5956166 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7552. Min Range: -5.7552
Max Act: 5.4115. Min Act: -0.1700
Data Index: 304847 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7552. Min Range: -5.7552
Max Act: 5.4115. Min Act: -0.1700
Data Index: 5080515 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19