Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5233 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9394. Min Range: -5.9394
Max Act: 5.9394. Min Act: -0.1700
Data Index: 2327347 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9394. Min Range: -5.9394
Max Act: 5.8144. Min Act: -0.1700
Data Index: 7136536 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9394. Min Range: -5.9394
Max Act: 5.8144. Min Act: -0.1700
Data Index: 6834067 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9394. Min Range: -5.9394
Max Act: 5.7519. Min Act: -0.1700
Data Index: 1311028 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9394. Min Range: -5.9394
Max Act: 5.7206. Min Act: -0.1700
Data Index: 8324467 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9394. Min Range: -5.9394
Max Act: 5.7206. Min Act: -0.1700
Data Index: 4943192 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9394. Min Range: -5.9394
Max Act: 5.6894. Min Act: -0.1700
Data Index: 4544366 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9394. Min Range: -5.9394
Max Act: 5.6269. Min Act: -0.1700
Data Index: 4890331 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9394. Min Range: -5.9394
Max Act: 5.6581. Min Act: -0.1700
Data Index: 3969043 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9394. Min Range: -5.9394
Max Act: 5.6269. Min Act: -0.1700
Data Index: 3535752 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9394. Min Range: -5.9394
Max Act: 5.6269. Min Act: -0.1700
Data Index: 6046493 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9394. Min Range: -5.9394
Max Act: 5.6269. Min Act: -0.1700
Data Index: 1445400 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9394. Min Range: -5.9394
Max Act: 5.5956. Min Act: -0.1700
Data Index: 7762334 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9394. Min Range: -5.9394
Max Act: 5.5956. Min Act: -0.1700
Data Index: 4694863 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9394. Min Range: -5.9394
Max Act: 5.5956. Min Act: -0.1700
Data Index: 6484774 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9394. Min Range: -5.9394
Max Act: 5.5956. Min Act: -0.1700
Data Index: 7682389 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9394. Min Range: -5.9394
Max Act: 5.5644. Min Act: -0.1700
Data Index: 2275087 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9394. Min Range: -5.9394
Max Act: 5.5644. Min Act: -0.1700
Data Index: 1915204 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9394. Min Range: -5.9394
Max Act: 5.5644. Min Act: -0.1700
Data Index: 6954780 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9394. Min Range: -5.9394
Max Act: 5.5644. Min Act: -0.1700
Data Index: 1073813 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19