Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2984 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4231. Min Range: -7.4231
Max Act: 7.4231. Min Act: -0.1700
Data Index: 8072586 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4231. Min Range: -7.4231
Max Act: 7.2668. Min Act: -0.1700
Data Index: 4628128 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4231. Min Range: -7.4231
Max Act: 7.2043. Min Act: -0.1700
Data Index: 7439744 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4231. Min Range: -7.4231
Max Act: 7.0168. Min Act: -0.1700
Data Index: 3279180 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4231. Min Range: -7.4231
Max Act: 6.8918. Min Act: -0.1700
Data Index: 6696229 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4231. Min Range: -7.4231
Max Act: 6.9231. Min Act: -0.1700
Data Index: 8031959 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4231. Min Range: -7.4231
Max Act: 6.9231. Min Act: -0.1700
Data Index: 7437346 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4231. Min Range: -7.4231
Max Act: 6.8918. Min Act: -0.1700
Data Index: 2909873 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4231. Min Range: -7.4231
Max Act: 6.8918. Min Act: -0.1700
Data Index: 302279 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4231. Min Range: -7.4231
Max Act: 6.8606. Min Act: -0.1700
Data Index: 3879841 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4231. Min Range: -7.4231
Max Act: 6.8606. Min Act: -0.1700
Data Index: 6553325 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4231. Min Range: -7.4231
Max Act: 6.8293. Min Act: -0.1700
Data Index: 713391 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4231. Min Range: -7.4231
Max Act: 6.8293. Min Act: -0.1700
Data Index: 843350 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4231. Min Range: -7.4231
Max Act: 6.7981. Min Act: -0.1700
Data Index: 6213751 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4231. Min Range: -7.4231
Max Act: 6.8293. Min Act: -0.1700
Data Index: 6142758 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4231. Min Range: -7.4231
Max Act: 6.7981. Min Act: -0.1700
Data Index: 6153747 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4231. Min Range: -7.4231
Max Act: 6.7668. Min Act: -0.1700
Data Index: 7200586 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4231. Min Range: -7.4231
Max Act: 6.7356. Min Act: -0.1700
Data Index: 5498962 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4231. Min Range: -7.4231
Max Act: 6.7043. Min Act: -0.1700
Data Index: 8286280 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4231. Min Range: -7.4231
Max Act: 6.7043. Min Act: -0.1700
Data Index: 6916910 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19