Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3778 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2332. Min Range: -6.2332
Max Act: 6.2332. Min Act: -0.1700
Data Index: 627888 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2332. Min Range: -6.2332
Max Act: 6.2332. Min Act: -0.1700
Data Index: 8239421 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2332. Min Range: -6.2332
Max Act: 6.2019. Min Act: -0.1700
Data Index: 5982548 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2332. Min Range: -6.2332
Max Act: 6.2019. Min Act: -0.1700
Data Index: 5881069 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2332. Min Range: -6.2332
Max Act: 6.1707. Min Act: -0.1700
Data Index: 5367739 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2332. Min Range: -6.2332
Max Act: 6.1394. Min Act: -0.1700
Data Index: 5855267 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2332. Min Range: -6.2332
Max Act: 6.1394. Min Act: -0.1700
Data Index: 331149 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2332. Min Range: -6.2332
Max Act: 6.1394. Min Act: -0.1700
Data Index: 7183189 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2332. Min Range: -6.2332
Max Act: 6.1394. Min Act: -0.1700
Data Index: 2492565 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2332. Min Range: -6.2332
Max Act: 6.1082. Min Act: -0.1700
Data Index: 934717 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2332. Min Range: -6.2332
Max Act: 6.1082. Min Act: -0.1700
Data Index: 638635 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2332. Min Range: -6.2332
Max Act: 6.1082. Min Act: -0.1700
Data Index: 69404 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2332. Min Range: -6.2332
Max Act: 6.1082. Min Act: -0.1698
Data Index: 719612 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2332. Min Range: -6.2332
Max Act: 6.1082. Min Act: -0.1700
Data Index: 1742315 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2332. Min Range: -6.2332
Max Act: 6.0769. Min Act: -0.1700
Data Index: 5401161 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2332. Min Range: -6.2332
Max Act: 6.0769. Min Act: -0.1700
Data Index: 5254389 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2332. Min Range: -6.2332
Max Act: 6.0769. Min Act: -0.1700
Data Index: 5889881 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2332. Min Range: -6.2332
Max Act: 6.0457. Min Act: -0.1700
Data Index: 1833163 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2332. Min Range: -6.2332
Max Act: 6.0769. Min Act: -0.1700
Data Index: 1756683 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2332. Min Range: -6.2332
Max Act: 6.0769. Min Act: -0.1700
Data Index: 8051966 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19