Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1405 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.5540. Min Act: -0.1700
Data Index: 8462274 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.3352. Min Act: -0.1700
Data Index: 2753656 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.3352. Min Act: -0.1700
Data Index: 8208922 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.3352. Min Act: -0.1700
Data Index: 7966220 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.3040. Min Act: -0.1700
Data Index: 2307408 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.2727. Min Act: -0.1700
Data Index: 5373491 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.2727. Min Act: -0.1700
Data Index: 228580 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.2102. Min Act: -0.1700
Data Index: 6624956 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.2102. Min Act: -0.1700
Data Index: 6582257 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.2102. Min Act: -0.1700
Data Index: 8284674 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.1477. Min Act: -0.1700
Data Index: 7692625 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.1165. Min Act: -0.1700
Data Index: 6844840 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.1165. Min Act: -0.1700
Data Index: 987127 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.1165. Min Act: -0.1700
Data Index: 8742791 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.0852. Min Act: -0.1700
Data Index: 1882238 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.0540. Min Act: -0.1700
Data Index: 6797256 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.0852. Min Act: -0.1700
Data Index: 6847723 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.0540. Min Act: -0.1700
Data Index: 6571309 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.0540. Min Act: -0.1700
Data Index: 2936668 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.0540. Min Act: -0.1700
Data Index: 5123724 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19