Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1732 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2244. Min Range: -8.2244
Max Act: 8.2244. Min Act: -0.1700
Data Index: 6717746 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.9119. Min Act: -0.1700
Data Index: 5579943 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.8494. Min Act: -0.1700
Data Index: 2629654 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.8494. Min Act: -0.1700
Data Index: 5713 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.9119. Min Act: -0.1700
Data Index: 3122878 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.8494. Min Act: -0.1700
Data Index: 294402 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.7869. Min Act: -0.1700
Data Index: 3114106 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.7869. Min Act: -0.1700
Data Index: 2075260 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.7244. Min Act: -0.1700
Data Index: 5716 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.7869. Min Act: -0.1700
Data Index: 2063938 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.6931. Min Act: -0.1700
Data Index: 211352 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.6619. Min Act: -0.1700
Data Index: 5718 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.6306. Min Act: -0.1700
Data Index: 7315400 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.6306. Min Act: -0.1700
Data Index: 1997441 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.5369. Min Act: -0.1700
Data Index: 1279205 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.5056. Min Act: -0.1700
Data Index: 6084360 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.5056. Min Act: -0.1700
Data Index: 3371530 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.5369. Min Act: -0.1700
Data Index: 1708601 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.4744. Min Act: -0.1700
Data Index: 4796223 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.4431. Min Act: -0.1700
Data Index: 3882108 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19