Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2960 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6754. Min Range: -8.6754
Max Act: 8.6754. Min Act: -0.1700
Data Index: 3841653 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6754. Min Range: -8.6754
Max Act: 7.6754. Min Act: -0.1700
Data Index: 7081664 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6754. Min Range: -8.6754
Max Act: 7.6129. Min Act: -0.1700
Data Index: 2576969 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6754. Min Range: -8.6754
Max Act: 7.5504. Min Act: -0.1700
Data Index: 11706 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6754. Min Range: -8.6754
Max Act: 7.3316. Min Act: -0.1700
Data Index: 8501527 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6754. Min Range: -8.6754
Max Act: 7.1441. Min Act: -0.1700
Data Index: 3451061 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6754. Min Range: -8.6754
Max Act: 7.1129. Min Act: -0.1700
Data Index: 6597416 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6754. Min Range: -8.6754
Max Act: 7.1129. Min Act: -0.1700
Data Index: 137814 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6754. Min Range: -8.6754
Max Act: 7.1129. Min Act: -0.1700
Data Index: 7317735 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6754. Min Range: -8.6754
Max Act: 7.0816. Min Act: -0.1700
Data Index: 4652509 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6754. Min Range: -8.6754
Max Act: 6.9254. Min Act: -0.1700
Data Index: 2888814 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6754. Min Range: -8.6754
Max Act: 6.8629. Min Act: -0.1700
Data Index: 5598003 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6754. Min Range: -8.6754
Max Act: 6.8004. Min Act: -0.1700
Data Index: 122709 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6754. Min Range: -8.6754
Max Act: 6.7691. Min Act: -0.1700
Data Index: 5896252 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6754. Min Range: -8.6754
Max Act: 6.7379. Min Act: -0.1700
Data Index: 5168547 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6754. Min Range: -8.6754
Max Act: 6.7691. Min Act: -0.1700
Data Index: 5120516 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6754. Min Range: -8.6754
Max Act: 6.7379. Min Act: -0.1700
Data Index: 8226693 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6754. Min Range: -8.6754
Max Act: 6.7066. Min Act: -0.1700
Data Index: 3150699 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6754. Min Range: -8.6754
Max Act: 6.6754. Min Act: -0.1700
Data Index: 6178634 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6754. Min Range: -8.6754
Max Act: 6.7066. Min Act: -0.1700
Data Index: 7406673 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19