Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3062 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6448. Min Range: -8.6448
Max Act: 8.6448. Min Act: -0.1700
Data Index: 558054 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6448. Min Range: -8.6448
Max Act: 7.7698. Min Act: -0.1700
Data Index: 7715739 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6448. Min Range: -8.6448
Max Act: 7.5823. Min Act: -0.1700
Data Index: 4534450 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6448. Min Range: -8.6448
Max Act: 7.5511. Min Act: -0.1700
Data Index: 4787518 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6448. Min Range: -8.6448
Max Act: 7.5198. Min Act: -0.1700
Data Index: 7503009 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6448. Min Range: -8.6448
Max Act: 7.4261. Min Act: -0.1700
Data Index: 5560000 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6448. Min Range: -8.6448
Max Act: 7.3636. Min Act: -0.1700
Data Index: 4623007 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6448. Min Range: -8.6448
Max Act: 7.3636. Min Act: -0.1700
Data Index: 8166538 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6448. Min Range: -8.6448
Max Act: 7.3323. Min Act: -0.1700
Data Index: 6707803 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6448. Min Range: -8.6448
Max Act: 7.3323. Min Act: -0.1700
Data Index: 3372779 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6448. Min Range: -8.6448
Max Act: 7.3323. Min Act: -0.1700
Data Index: 2587815 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6448. Min Range: -8.6448
Max Act: 7.3323. Min Act: -0.1700
Data Index: 252405 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6448. Min Range: -8.6448
Max Act: 7.3011. Min Act: -0.1700
Data Index: 8166541 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6448. Min Range: -8.6448
Max Act: 7.2386. Min Act: -0.1700
Data Index: 6272128 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6448. Min Range: -8.6448
Max Act: 7.2073. Min Act: -0.1700
Data Index: 6783402 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6448. Min Range: -8.6448
Max Act: 7.2073. Min Act: -0.1700
Data Index: 423352 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6448. Min Range: -8.6448
Max Act: 7.1761. Min Act: -0.1700
Data Index: 2532778 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6448. Min Range: -8.6448
Max Act: 7.1448. Min Act: -0.1700
Data Index: 2505397 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6448. Min Range: -8.6448
Max Act: 7.1136. Min Act: -0.1700
Data Index: 7650434 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6448. Min Range: -8.6448
Max Act: 7.0511. Min Act: -0.1700
Data Index: 4536807 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19