Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 765 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9186. Min Range: -2.9186
Max Act: 2.9186. Min Act: -0.1700
Data Index: 5943388 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9186. Min Range: -2.9186
Max Act: 2.6316. Min Act: -0.1700
Data Index: 4676579 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9186. Min Range: -2.9186
Max Act: 2.6155. Min Act: -0.1700
Data Index: 2658161 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9186. Min Range: -2.9186
Max Act: 2.6155. Min Act: -0.1700
Data Index: 3537600 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9186. Min Range: -2.9186
Max Act: 2.5349. Min Act: -0.1699
Data Index: 5266431 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9186. Min Range: -2.9186
Max Act: 2.5187. Min Act: -0.1700
Data Index: 1292878 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9186. Min Range: -2.9186
Max Act: 2.4701. Min Act: -0.1695
Data Index: 5835780 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9186. Min Range: -2.9186
Max Act: 2.4539. Min Act: -0.1700
Data Index: 5435414 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9186. Min Range: -2.9186
Max Act: 2.4376. Min Act: -0.1699
Data Index: 4964112 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9186. Min Range: -2.9186
Max Act: 2.4376. Min Act: -0.1700
Data Index: 8103908 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9186. Min Range: -2.9186
Max Act: 2.4213. Min Act: -0.1693
Data Index: 7307943 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9186. Min Range: -2.9186
Max Act: 2.4213. Min Act: -0.1697
Data Index: 2621187 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9186. Min Range: -2.9186
Max Act: 2.4213. Min Act: -0.1700
Data Index: 8137178 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9186. Min Range: -2.9186
Max Act: 2.4213. Min Act: -0.1700
Data Index: 487899 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9186. Min Range: -2.9186
Max Act: 2.4213. Min Act: -0.1686
Data Index: 3031700 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9186. Min Range: -2.9186
Max Act: 2.4213. Min Act: -0.1700
Data Index: 5265789 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9186. Min Range: -2.9186
Max Act: 2.3887. Min Act: -0.1683
Data Index: 527484 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9186. Min Range: -2.9186
Max Act: 2.3887. Min Act: -0.1685
Data Index: 7967694 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9186. Min Range: -2.9186
Max Act: 2.3724. Min Act: -0.1700
Data Index: 7114201 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9186. Min Range: -2.9186
Max Act: 2.3724. Min Act: -0.1700
Data Index: 3699973 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19