Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3695 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4486. Min Range: -11.4486
Max Act: 11.4486. Min Act: -0.1700
Data Index: 8386172 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4486. Min Range: -11.4486
Max Act: 11.3861. Min Act: -0.1700
Data Index: 3053090 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4486. Min Range: -11.4486
Max Act: 11.3236. Min Act: -0.1700
Data Index: 183148 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4486. Min Range: -11.4486
Max Act: 11.3236. Min Act: -0.1700
Data Index: 5773371 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4486. Min Range: -11.4486
Max Act: 11.2611. Min Act: -0.1700
Data Index: 1308596 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4486. Min Range: -11.4486
Max Act: 11.1361. Min Act: -0.1700
Data Index: 7643486 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4486. Min Range: -11.4486
Max Act: 11.0111. Min Act: -0.1700
Data Index: 7896347 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4486. Min Range: -11.4486
Max Act: 11.0111. Min Act: -0.1700
Data Index: 1861752 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4486. Min Range: -11.4486
Max Act: 11.0111. Min Act: -0.1700
Data Index: 964461 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4486. Min Range: -11.4486
Max Act: 11.0111. Min Act: -0.1700
Data Index: 1636238 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4486. Min Range: -11.4486
Max Act: 11.0111. Min Act: -0.1700
Data Index: 760661 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4486. Min Range: -11.4486
Max Act: 11.0111. Min Act: -0.1700
Data Index: 72726 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4486. Min Range: -11.4486
Max Act: 10.8861. Min Act: -0.1700
Data Index: 1782835 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4486. Min Range: -11.4486
Max Act: 10.9486. Min Act: -0.1700
Data Index: 2647455 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4486. Min Range: -11.4486
Max Act: 10.9486. Min Act: -0.1700
Data Index: 936777 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4486. Min Range: -11.4486
Max Act: 10.9486. Min Act: -0.1700
Data Index: 7857020 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4486. Min Range: -11.4486
Max Act: 10.8236. Min Act: -0.1700
Data Index: 4586673 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4486. Min Range: -11.4486
Max Act: 10.8861. Min Act: -0.1700
Data Index: 4741049 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4486. Min Range: -11.4486
Max Act: 10.8236. Min Act: -0.1700
Data Index: 3913813 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4486. Min Range: -11.4486
Max Act: 10.8236. Min Act: -0.1700
Data Index: 6960377 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19