Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2603 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6394. Min Range: -8.6394
Max Act: 8.6394. Min Act: -0.1700
Data Index: 3829381 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6394. Min Range: -8.6394
Max Act: 8.4519. Min Act: -0.1700
Data Index: 7703346 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6394. Min Range: -8.6394
Max Act: 8.4206. Min Act: -0.1700
Data Index: 5460261 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6394. Min Range: -8.6394
Max Act: 8.1706. Min Act: -0.1700
Data Index: 1108276 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6394. Min Range: -8.6394
Max Act: 8.0769. Min Act: -0.1700
Data Index: 7254084 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6394. Min Range: -8.6394
Max Act: 8.0144. Min Act: -0.1700
Data Index: 2469249 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6394. Min Range: -8.6394
Max Act: 8.0144. Min Act: -0.1700
Data Index: 4227616 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6394. Min Range: -8.6394
Max Act: 7.9519. Min Act: -0.1700
Data Index: 5477154 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6394. Min Range: -8.6394
Max Act: 7.9206. Min Act: -0.1700
Data Index: 2891088 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6394. Min Range: -8.6394
Max Act: 7.9519. Min Act: -0.1700
Data Index: 3805170 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6394. Min Range: -8.6394
Max Act: 7.8269. Min Act: -0.1700
Data Index: 1265076 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6394. Min Range: -8.6394
Max Act: 7.7956. Min Act: -0.1700
Data Index: 3384194 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6394. Min Range: -8.6394
Max Act: 7.7644. Min Act: -0.1700
Data Index: 6164357 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6394. Min Range: -8.6394
Max Act: 7.7644. Min Act: -0.1700
Data Index: 2295231 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6394. Min Range: -8.6394
Max Act: 7.7331. Min Act: -0.1700
Data Index: 7744705 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6394. Min Range: -8.6394
Max Act: 7.7644. Min Act: -0.1700
Data Index: 3310613 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6394. Min Range: -8.6394
Max Act: 7.7331. Min Act: -0.1700
Data Index: 2126502 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6394. Min Range: -8.6394
Max Act: 7.7019. Min Act: -0.1700
Data Index: 2714991 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6394. Min Range: -8.6394
Max Act: 7.7019. Min Act: -0.1700
Data Index: 2045713 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6394. Min Range: -8.6394
Max Act: 7.6706. Min Act: -0.1700
Data Index: 3313710 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19