Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 256 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0211. Min Range: -8.0211
Max Act: 8.0211. Min Act: -0.1700
Data Index: 6422486 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0211. Min Range: -8.0211
Max Act: 7.8961. Min Act: -0.1700
Data Index: 6250724 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0211. Min Range: -8.0211
Max Act: 7.7711. Min Act: -0.1700
Data Index: 8301016 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0211. Min Range: -8.0211
Max Act: 7.7086. Min Act: -0.1700
Data Index: 7783837 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0211. Min Range: -8.0211
Max Act: 7.6461. Min Act: -0.1700
Data Index: 5160233 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0211. Min Range: -8.0211
Max Act: 7.5836. Min Act: -0.1700
Data Index: 8240228 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0211. Min Range: -8.0211
Max Act: 7.5836. Min Act: -0.1700
Data Index: 5936151 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0211. Min Range: -8.0211
Max Act: 7.5211. Min Act: -0.1700
Data Index: 3778552 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0211. Min Range: -8.0211
Max Act: 7.5524. Min Act: -0.1700
Data Index: 8337912 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0211. Min Range: -8.0211
Max Act: 7.4899. Min Act: -0.1700
Data Index: 1885998 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0211. Min Range: -8.0211
Max Act: 7.5211. Min Act: -0.1700
Data Index: 2956119 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0211. Min Range: -8.0211
Max Act: 7.5211. Min Act: -0.1700
Data Index: 8778414 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0211. Min Range: -8.0211
Max Act: 7.4899. Min Act: -0.1700
Data Index: 5562614 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0211. Min Range: -8.0211
Max Act: 7.5211. Min Act: -0.1700
Data Index: 8818772 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0211. Min Range: -8.0211
Max Act: 7.4899. Min Act: -0.1700
Data Index: 8020657 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0211. Min Range: -8.0211
Max Act: 7.4899. Min Act: -0.1700
Data Index: 4967951 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0211. Min Range: -8.0211
Max Act: 7.4274. Min Act: -0.1700
Data Index: 2336980 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0211. Min Range: -8.0211
Max Act: 7.4586. Min Act: -0.1700
Data Index: 6199351 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0211. Min Range: -8.0211
Max Act: 7.3961. Min Act: -0.1700
Data Index: 7731836 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0211. Min Range: -8.0211
Max Act: 7.3961. Min Act: -0.1700
Data Index: 6530025 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19