Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2820 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4002. Min Range: -8.4002
Max Act: 8.4002. Min Act: -0.1700
Data Index: 2069335 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4002. Min Range: -8.4002
Max Act: 8.0877. Min Act: -0.1700
Data Index: 7128900 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4002. Min Range: -8.4002
Max Act: 7.9627. Min Act: -0.1700
Data Index: 6540140 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4002. Min Range: -8.4002
Max Act: 7.9315. Min Act: -0.1700
Data Index: 7662273 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4002. Min Range: -8.4002
Max Act: 7.9315. Min Act: -0.1700
Data Index: 6097141 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4002. Min Range: -8.4002
Max Act: 7.9002. Min Act: -0.1700
Data Index: 2072254 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4002. Min Range: -8.4002
Max Act: 7.8065. Min Act: -0.1700
Data Index: 5977849 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4002. Min Range: -8.4002
Max Act: 7.7127. Min Act: -0.1700
Data Index: 6491967 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4002. Min Range: -8.4002
Max Act: 7.7127. Min Act: -0.1700
Data Index: 6178057 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4002. Min Range: -8.4002
Max Act: 7.7127. Min Act: -0.1700
Data Index: 1214766 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4002. Min Range: -8.4002
Max Act: 7.6815. Min Act: -0.1700
Data Index: 6670078 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4002. Min Range: -8.4002
Max Act: 7.6815. Min Act: -0.1700
Data Index: 2814678 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4002. Min Range: -8.4002
Max Act: 7.6815. Min Act: -0.1700
Data Index: 5391792 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4002. Min Range: -8.4002
Max Act: 7.6815. Min Act: -0.1700
Data Index: 574841 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4002. Min Range: -8.4002
Max Act: 7.6502. Min Act: -0.1700
Data Index: 6036424 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4002. Min Range: -8.4002
Max Act: 7.6502. Min Act: -0.1700
Data Index: 249859 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4002. Min Range: -8.4002
Max Act: 7.6502. Min Act: -0.1700
Data Index: 3770276 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4002. Min Range: -8.4002
Max Act: 7.5877. Min Act: -0.1700
Data Index: 2485713 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4002. Min Range: -8.4002
Max Act: 7.5877. Min Act: -0.1700
Data Index: 7151429 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4002. Min Range: -8.4002
Max Act: 7.5877. Min Act: -0.1700
Data Index: 7582256 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19