Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4648 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4847. Min Range: -7.4847
Max Act: 7.4847. Min Act: -0.1700
Data Index: 2800135 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4847. Min Range: -7.4847
Max Act: 7.2659. Min Act: -0.1700
Data Index: 6174614 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4847. Min Range: -7.4847
Max Act: 7.0784. Min Act: -0.1700
Data Index: 7839898 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4847. Min Range: -7.4847
Max Act: 7.0159. Min Act: -0.1700
Data Index: 1260034 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4847. Min Range: -7.4847
Max Act: 6.9847. Min Act: -0.1700
Data Index: 6551413 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4847. Min Range: -7.4847
Max Act: 6.8597. Min Act: -0.1700
Data Index: 5937146 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4847. Min Range: -7.4847
Max Act: 6.8284. Min Act: -0.1700
Data Index: 6173190 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4847. Min Range: -7.4847
Max Act: 6.7972. Min Act: -0.1700
Data Index: 1441515 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4847. Min Range: -7.4847
Max Act: 6.7347. Min Act: -0.1700
Data Index: 2536863 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4847. Min Range: -7.4847
Max Act: 6.7347. Min Act: -0.1700
Data Index: 4974425 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4847. Min Range: -7.4847
Max Act: 6.7659. Min Act: -0.1700
Data Index: 6443228 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4847. Min Range: -7.4847
Max Act: 6.6722. Min Act: -0.1700
Data Index: 3978668 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4847. Min Range: -7.4847
Max Act: 6.6409. Min Act: -0.1700
Data Index: 8092470 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4847. Min Range: -7.4847
Max Act: 6.6722. Min Act: -0.1700
Data Index: 4095650 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4847. Min Range: -7.4847
Max Act: 6.6409. Min Act: -0.1700
Data Index: 76102 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4847. Min Range: -7.4847
Max Act: 6.6097. Min Act: -0.1700
Data Index: 3154804 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4847. Min Range: -7.4847
Max Act: 6.6409. Min Act: -0.1700
Data Index: 2232651 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4847. Min Range: -7.4847
Max Act: 6.5472. Min Act: -0.1700
Data Index: 6541470 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4847. Min Range: -7.4847
Max Act: 6.5784. Min Act: -0.1700
Data Index: 7172821 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4847. Min Range: -7.4847
Max Act: 6.5784. Min Act: -0.1700
Data Index: 1887100 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19