Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5017 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0236. Min Range: -5.0236
Max Act: 5.0236. Min Act: -0.1699
Data Index: 7138315 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0236. Min Range: -5.0236
Max Act: 4.8048. Min Act: -0.1700
Data Index: 8458401 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0236. Min Range: -5.0236
Max Act: 4.6798. Min Act: -0.1700
Data Index: 3596018 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0236. Min Range: -5.0236
Max Act: 4.6173. Min Act: -0.1697
Data Index: 614444 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0236. Min Range: -5.0236
Max Act: 4.6486. Min Act: -0.1700
Data Index: 2919570 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0236. Min Range: -5.0236
Max Act: 4.5861. Min Act: -0.1700
Data Index: 5944428 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0236. Min Range: -5.0236
Max Act: 4.6486. Min Act: -0.1700
Data Index: 828702 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0236. Min Range: -5.0236
Max Act: 4.6173. Min Act: -0.1699
Data Index: 1999996 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0236. Min Range: -5.0236
Max Act: 4.6173. Min Act: -0.1700
Data Index: 5349631 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0236. Min Range: -5.0236
Max Act: 4.5236. Min Act: -0.1700
Data Index: 6248337 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0236. Min Range: -5.0236
Max Act: 4.5548. Min Act: -0.1700
Data Index: 8078361 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0236. Min Range: -5.0236
Max Act: 4.5236. Min Act: -0.1700
Data Index: 1967386 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0236. Min Range: -5.0236
Max Act: 4.5236. Min Act: -0.1699
Data Index: 3219101 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0236. Min Range: -5.0236
Max Act: 4.5236. Min Act: -0.1700
Data Index: 5497362 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0236. Min Range: -5.0236
Max Act: 4.5236. Min Act: -0.1700
Data Index: 276213 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0236. Min Range: -5.0236
Max Act: 4.4923. Min Act: -0.1700
Data Index: 8385862 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0236. Min Range: -5.0236
Max Act: 4.4923. Min Act: -0.1700
Data Index: 3895956 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0236. Min Range: -5.0236
Max Act: 4.4611. Min Act: -0.1699
Data Index: 7197680 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0236. Min Range: -5.0236
Max Act: 4.4923. Min Act: -0.1700
Data Index: 1273791 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0236. Min Range: -5.0236
Max Act: 4.4923. Min Act: -0.1700
Data Index: 5280235 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19