Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5165 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6292. Min Range: -7.6292
Max Act: 7.6292. Min Act: -0.1700
Data Index: 3384298 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6292. Min Range: -7.6292
Max Act: 7.5354. Min Act: -0.1700
Data Index: 6748427 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6292. Min Range: -7.6292
Max Act: 7.3167. Min Act: -0.1700
Data Index: 4919854 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6292. Min Range: -7.6292
Max Act: 7.2229. Min Act: -0.1700
Data Index: 1380391 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6292. Min Range: -7.6292
Max Act: 7.2229. Min Act: -0.1700
Data Index: 2923404 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6292. Min Range: -7.6292
Max Act: 7.1917. Min Act: -0.1700
Data Index: 8189574 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6292. Min Range: -7.6292
Max Act: 7.1604. Min Act: -0.1700
Data Index: 8181693 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6292. Min Range: -7.6292
Max Act: 7.1917. Min Act: -0.1700
Data Index: 7650701 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6292. Min Range: -7.6292
Max Act: 7.1917. Min Act: -0.1700
Data Index: 777493 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6292. Min Range: -7.6292
Max Act: 7.1292. Min Act: -0.1700
Data Index: 8078637 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6292. Min Range: -7.6292
Max Act: 7.0979. Min Act: -0.1700
Data Index: 3708030 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6292. Min Range: -7.6292
Max Act: 7.1292. Min Act: -0.1700
Data Index: 90111 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6292. Min Range: -7.6292
Max Act: 7.0979. Min Act: -0.1700
Data Index: 5321982 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6292. Min Range: -7.6292
Max Act: 7.0979. Min Act: -0.1700
Data Index: 6602192 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6292. Min Range: -7.6292
Max Act: 7.0979. Min Act: -0.1700
Data Index: 2193066 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6292. Min Range: -7.6292
Max Act: 7.0667. Min Act: -0.1700
Data Index: 1042805 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6292. Min Range: -7.6292
Max Act: 7.0667. Min Act: -0.1700
Data Index: 2096401 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6292. Min Range: -7.6292
Max Act: 7.0667. Min Act: -0.1700
Data Index: 692739 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6292. Min Range: -7.6292
Max Act: 7.0042. Min Act: -0.1700
Data Index: 7079037 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6292. Min Range: -7.6292
Max Act: 6.9729. Min Act: -0.1700
Data Index: 1487969 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19