Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 540 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6677. Min Range: -8.6677
Max Act: 8.6677. Min Act: -0.1700
Data Index: 4028645 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6677. Min Range: -8.6677
Max Act: 8.4177. Min Act: -0.1700
Data Index: 6767639 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6677. Min Range: -8.6677
Max Act: 8.3552. Min Act: -0.1700
Data Index: 5016290 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6677. Min Range: -8.6677
Max Act: 8.2927. Min Act: -0.1700
Data Index: 158683 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6677. Min Range: -8.6677
Max Act: 8.2302. Min Act: -0.1700
Data Index: 3929533 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6677. Min Range: -8.6677
Max Act: 8.1677. Min Act: -0.1700
Data Index: 368951 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6677. Min Range: -8.6677
Max Act: 8.0427. Min Act: -0.1700
Data Index: 734497 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6677. Min Range: -8.6677
Max Act: 8.1052. Min Act: -0.1700
Data Index: 939911 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6677. Min Range: -8.6677
Max Act: 8.0115. Min Act: -0.1700
Data Index: 5594472 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6677. Min Range: -8.6677
Max Act: 7.9490. Min Act: -0.1700
Data Index: 4742580 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6677. Min Range: -8.6677
Max Act: 7.9802. Min Act: -0.1700
Data Index: 1721950 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6677. Min Range: -8.6677
Max Act: 7.9177. Min Act: -0.1700
Data Index: 8456865 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6677. Min Range: -8.6677
Max Act: 7.9177. Min Act: -0.1700
Data Index: 3729772 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6677. Min Range: -8.6677
Max Act: 7.8240. Min Act: -0.1700
Data Index: 6832207 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6677. Min Range: -8.6677
Max Act: 7.8240. Min Act: -0.1700
Data Index: 5114019 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6677. Min Range: -8.6677
Max Act: 7.7927. Min Act: -0.1700
Data Index: 7602350 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6677. Min Range: -8.6677
Max Act: 7.7927. Min Act: -0.1700
Data Index: 758551 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6677. Min Range: -8.6677
Max Act: 7.7615. Min Act: -0.1700
Data Index: 3598397 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6677. Min Range: -8.6677
Max Act: 7.7615. Min Act: -0.1700
Data Index: 8635587 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6677. Min Range: -8.6677
Max Act: 7.7927. Min Act: -0.1700
Data Index: 6380760 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19