Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3869 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5779. Min Range: -6.5779
Max Act: 6.5779. Min Act: -0.1700
Data Index: 1256567 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5779. Min Range: -6.5779
Max Act: 6.5467. Min Act: -0.1699
Data Index: 5169026 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5779. Min Range: -6.5779
Max Act: 6.5467. Min Act: -0.1693
Data Index: 8673658 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5779. Min Range: -6.5779
Max Act: 6.5467. Min Act: -0.1379
Data Index: 7993655 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5779. Min Range: -6.5779
Max Act: 6.5154. Min Act: -0.1700
Data Index: 888979 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5779. Min Range: -6.5779
Max Act: 6.4842. Min Act: -0.1488
Data Index: 5756550 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5779. Min Range: -6.5779
Max Act: 6.4529. Min Act: -0.1700
Data Index: 5197774 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5779. Min Range: -6.5779
Max Act: 6.4529. Min Act: -0.1696
Data Index: 6057529 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5779. Min Range: -6.5779
Max Act: 6.4529. Min Act: -0.1557
Data Index: 5756549 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5779. Min Range: -6.5779
Max Act: 6.4217. Min Act: -0.1683
Data Index: 5756543 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5779. Min Range: -6.5779
Max Act: 6.3904. Min Act: -0.1700
Data Index: 5809368 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5779. Min Range: -6.5779
Max Act: 6.3592. Min Act: -0.1658
Data Index: 809892 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5779. Min Range: -6.5779
Max Act: 6.3279. Min Act: -0.1700
Data Index: 7507397 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5779. Min Range: -6.5779
Max Act: 6.3279. Min Act: -0.1621
Data Index: 96394 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5779. Min Range: -6.5779
Max Act: 6.2967. Min Act: -0.1678
Data Index: 2946048 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5779. Min Range: -6.5779
Max Act: 6.2967. Min Act: -0.1687
Data Index: 7727415 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5779. Min Range: -6.5779
Max Act: 6.2967. Min Act: -0.1700
Data Index: 540179 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5779. Min Range: -6.5779
Max Act: 6.2967. Min Act: -0.1618
Data Index: 807004 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5779. Min Range: -6.5779
Max Act: 6.2342. Min Act: -0.1700
Data Index: 1129817 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5779. Min Range: -6.5779
Max Act: 6.2342. Min Act: -0.1700
Data Index: 3633541 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19