Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2862 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5118. Min Range: -7.5118
Max Act: 7.5118. Min Act: -0.1700
Data Index: 3914449 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5118. Min Range: -7.5118
Max Act: 7.1368. Min Act: -0.1700
Data Index: 7095997 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5118. Min Range: -7.5118
Max Act: 7.1056. Min Act: -0.1700
Data Index: 2832310 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5118. Min Range: -7.5118
Max Act: 6.9806. Min Act: -0.1700
Data Index: 1998567 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5118. Min Range: -7.5118
Max Act: 6.9181. Min Act: -0.1700
Data Index: 1897019 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5118. Min Range: -7.5118
Max Act: 6.7931. Min Act: -0.1700
Data Index: 8688390 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5118. Min Range: -7.5118
Max Act: 6.7618. Min Act: -0.1700
Data Index: 6739147 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5118. Min Range: -7.5118
Max Act: 6.7618. Min Act: -0.1700
Data Index: 2298378 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5118. Min Range: -7.5118
Max Act: 6.7306. Min Act: -0.1700
Data Index: 5429309 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5118. Min Range: -7.5118
Max Act: 6.6993. Min Act: -0.1700
Data Index: 1425335 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5118. Min Range: -7.5118
Max Act: 6.6993. Min Act: -0.1700
Data Index: 2075856 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5118. Min Range: -7.5118
Max Act: 6.6368. Min Act: -0.1700
Data Index: 7277705 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5118. Min Range: -7.5118
Max Act: 6.6368. Min Act: -0.1700
Data Index: 6294392 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5118. Min Range: -7.5118
Max Act: 6.6056. Min Act: -0.1700
Data Index: 7438404 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5118. Min Range: -7.5118
Max Act: 6.5743. Min Act: -0.1700
Data Index: 6468608 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5118. Min Range: -7.5118
Max Act: 6.5118. Min Act: -0.1700
Data Index: 1788325 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5118. Min Range: -7.5118
Max Act: 6.4806. Min Act: -0.1700
Data Index: 6777464 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5118. Min Range: -7.5118
Max Act: 6.4806. Min Act: -0.1700
Data Index: 1358829 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5118. Min Range: -7.5118
Max Act: 6.4493. Min Act: -0.1700
Data Index: 1769308 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5118. Min Range: -7.5118
Max Act: 6.4493. Min Act: -0.1700
Data Index: 6090659 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19