Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2037 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6814. Min Range: -5.6814
Max Act: 5.6814. Min Act: -0.1700
Data Index: 4283536 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6814. Min Range: -5.6814
Max Act: 5.6502. Min Act: -0.1700
Data Index: 179776 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6814. Min Range: -5.6814
Max Act: 5.6502. Min Act: -0.1700
Data Index: 7888135 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6814. Min Range: -5.6814
Max Act: 5.6189. Min Act: -0.1700
Data Index: 7833910 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6814. Min Range: -5.6814
Max Act: 5.5564. Min Act: -0.1700
Data Index: 4914623 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6814. Min Range: -5.6814
Max Act: 5.5252. Min Act: -0.1700
Data Index: 5091692 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6814. Min Range: -5.6814
Max Act: 5.5252. Min Act: -0.1700
Data Index: 8511054 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6814. Min Range: -5.6814
Max Act: 5.5252. Min Act: -0.1700
Data Index: 4860686 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6814. Min Range: -5.6814
Max Act: 5.4939. Min Act: -0.1700
Data Index: 3732243 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6814. Min Range: -5.6814
Max Act: 5.4939. Min Act: -0.1700
Data Index: 4806346 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6814. Min Range: -5.6814
Max Act: 5.4627. Min Act: -0.1700
Data Index: 1279175 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6814. Min Range: -5.6814
Max Act: 5.4939. Min Act: -0.1700
Data Index: 5385561 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6814. Min Range: -5.6814
Max Act: 5.4627. Min Act: -0.1700
Data Index: 5972198 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6814. Min Range: -5.6814
Max Act: 5.4627. Min Act: -0.1700
Data Index: 1237826 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6814. Min Range: -5.6814
Max Act: 5.4939. Min Act: -0.1700
Data Index: 5617560 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6814. Min Range: -5.6814
Max Act: 5.4627. Min Act: -0.1700
Data Index: 7936576 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6814. Min Range: -5.6814
Max Act: 5.4314. Min Act: -0.1700
Data Index: 3833711 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6814. Min Range: -5.6814
Max Act: 5.4002. Min Act: -0.1700
Data Index: 3527295 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6814. Min Range: -5.6814
Max Act: 5.4314. Min Act: -0.1700
Data Index: 1794201 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6814. Min Range: -5.6814
Max Act: 5.4314. Min Act: -0.1700
Data Index: 5161968 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19