Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1234 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6374. Min Range: -7.6374
Max Act: 7.6374. Min Act: -0.1700
Data Index: 5619035 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6374. Min Range: -7.6374
Max Act: 7.5436. Min Act: -0.1700
Data Index: 6082017 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6374. Min Range: -7.6374
Max Act: 7.3249. Min Act: -0.1700
Data Index: 1076095 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6374. Min Range: -7.6374
Max Act: 7.1374. Min Act: -0.1700
Data Index: 1632826 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6374. Min Range: -7.6374
Max Act: 7.1374. Min Act: -0.1700
Data Index: 912086 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6374. Min Range: -7.6374
Max Act: 7.1374. Min Act: -0.1700
Data Index: 8634337 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6374. Min Range: -7.6374
Max Act: 7.0749. Min Act: -0.1700
Data Index: 496747 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6374. Min Range: -7.6374
Max Act: 7.0749. Min Act: -0.1700
Data Index: 2871169 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6374. Min Range: -7.6374
Max Act: 7.0749. Min Act: -0.1700
Data Index: 4717452 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6374. Min Range: -7.6374
Max Act: 7.0124. Min Act: -0.1700
Data Index: 6397678 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6374. Min Range: -7.6374
Max Act: 7.0436. Min Act: -0.1700
Data Index: 5258884 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6374. Min Range: -7.6374
Max Act: 7.0124. Min Act: -0.1700
Data Index: 4241439 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6374. Min Range: -7.6374
Max Act: 6.9811. Min Act: -0.1700
Data Index: 8612161 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6374. Min Range: -7.6374
Max Act: 6.9499. Min Act: -0.1700
Data Index: 1996363 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6374. Min Range: -7.6374
Max Act: 6.9499. Min Act: -0.1700
Data Index: 6784776 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6374. Min Range: -7.6374
Max Act: 6.9499. Min Act: -0.1700
Data Index: 8720467 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6374. Min Range: -7.6374
Max Act: 6.9186. Min Act: -0.1700
Data Index: 2034176 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6374. Min Range: -7.6374
Max Act: 6.9186. Min Act: -0.1700
Data Index: 5242810 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6374. Min Range: -7.6374
Max Act: 6.8874. Min Act: -0.1700
Data Index: 7148512 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6374. Min Range: -7.6374
Max Act: 6.8874. Min Act: -0.1700
Data Index: 1939889 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19