Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4007 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7206. Min Range: -5.7206
Max Act: 5.7206. Min Act: -0.1700
Data Index: 87838 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7206. Min Range: -5.7206
Max Act: 5.7206. Min Act: -0.1700
Data Index: 1240674 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7206. Min Range: -5.7206
Max Act: 5.6581. Min Act: -0.1700
Data Index: 1984179 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7206. Min Range: -5.7206
Max Act: 5.6268. Min Act: -0.1700
Data Index: 7210907 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7206. Min Range: -5.7206
Max Act: 5.5956. Min Act: -0.1700
Data Index: 5247776 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7206. Min Range: -5.7206
Max Act: 5.5643. Min Act: -0.1700
Data Index: 3288837 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7206. Min Range: -5.7206
Max Act: 5.5331. Min Act: -0.1700
Data Index: 3851099 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7206. Min Range: -5.7206
Max Act: 5.5643. Min Act: -0.1700
Data Index: 7745583 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7206. Min Range: -5.7206
Max Act: 5.5018. Min Act: -0.1700
Data Index: 3279040 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7206. Min Range: -5.7206
Max Act: 5.5018. Min Act: -0.1700
Data Index: 8532773 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7206. Min Range: -5.7206
Max Act: 5.5018. Min Act: -0.1700
Data Index: 2172236 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7206. Min Range: -5.7206
Max Act: 5.5018. Min Act: -0.1700
Data Index: 5286330 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7206. Min Range: -5.7206
Max Act: 5.4706. Min Act: -0.1700
Data Index: 8272057 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7206. Min Range: -5.7206
Max Act: 5.4393. Min Act: -0.1700
Data Index: 6208770 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7206. Min Range: -5.7206
Max Act: 5.3768. Min Act: -0.1700
Data Index: 3858566 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7206. Min Range: -5.7206
Max Act: 5.4081. Min Act: -0.1700
Data Index: 6789584 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7206. Min Range: -5.7206
Max Act: 5.4081. Min Act: -0.1700
Data Index: 1225466 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7206. Min Range: -5.7206
Max Act: 5.4081. Min Act: -0.1700
Data Index: 4660520 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7206. Min Range: -5.7206
Max Act: 5.4081. Min Act: -0.1700
Data Index: 7788045 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7206. Min Range: -5.7206
Max Act: 5.4081. Min Act: -0.1700
Data Index: 227818 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19