Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3826 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9346. Min Range: -6.9346
Max Act: 6.9346. Min Act: -0.1700
Data Index: 282969 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9346. Min Range: -6.9346
Max Act: 6.7783. Min Act: -0.1700
Data Index: 3105461 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9346. Min Range: -6.9346
Max Act: 6.7783. Min Act: -0.1700
Data Index: 4022626 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9346. Min Range: -6.9346
Max Act: 6.7471. Min Act: -0.1700
Data Index: 5789817 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9346. Min Range: -6.9346
Max Act: 6.7471. Min Act: -0.1700
Data Index: 2896491 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9346. Min Range: -6.9346
Max Act: 6.6846. Min Act: -0.1700
Data Index: 1930792 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9346. Min Range: -6.9346
Max Act: 6.6846. Min Act: -0.1700
Data Index: 96299 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9346. Min Range: -6.9346
Max Act: 6.6221. Min Act: -0.1700
Data Index: 1346443 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9346. Min Range: -6.9346
Max Act: 6.6221. Min Act: -0.1700
Data Index: 2178980 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9346. Min Range: -6.9346
Max Act: 6.5596. Min Act: -0.1700
Data Index: 1165671 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9346. Min Range: -6.9346
Max Act: 6.5596. Min Act: -0.1700
Data Index: 4752592 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9346. Min Range: -6.9346
Max Act: 6.5283. Min Act: -0.1700
Data Index: 2098358 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9346. Min Range: -6.9346
Max Act: 6.5283. Min Act: -0.1700
Data Index: 884421 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9346. Min Range: -6.9346
Max Act: 6.5283. Min Act: -0.1700
Data Index: 4527123 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9346. Min Range: -6.9346
Max Act: 6.5283. Min Act: -0.1700
Data Index: 4370760 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9346. Min Range: -6.9346
Max Act: 6.4971. Min Act: -0.1700
Data Index: 8811228 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9346. Min Range: -6.9346
Max Act: 6.4658. Min Act: -0.1700
Data Index: 2350832 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9346. Min Range: -6.9346
Max Act: 6.4346. Min Act: -0.1700
Data Index: 4656862 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9346. Min Range: -6.9346
Max Act: 6.4346. Min Act: -0.1700
Data Index: 6382795 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9346. Min Range: -6.9346
Max Act: 6.4033. Min Act: -0.1700
Data Index: 1956774 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19