Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3565 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5443. Min Range: -6.5443
Max Act: 6.5443. Min Act: -0.1700
Data Index: 3296183 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5443. Min Range: -6.5443
Max Act: 6.4818. Min Act: -0.1700
Data Index: 1004695 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5443. Min Range: -6.5443
Max Act: 6.4506. Min Act: -0.1700
Data Index: 4795332 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5443. Min Range: -6.5443
Max Act: 6.4193. Min Act: -0.1700
Data Index: 835561 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5443. Min Range: -6.5443
Max Act: 6.3256. Min Act: -0.1700
Data Index: 4864074 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5443. Min Range: -6.5443
Max Act: 6.3256. Min Act: -0.1700
Data Index: 724157 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5443. Min Range: -6.5443
Max Act: 6.2943. Min Act: -0.1700
Data Index: 6942770 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5443. Min Range: -6.5443
Max Act: 6.2006. Min Act: -0.1700
Data Index: 7400681 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5443. Min Range: -6.5443
Max Act: 6.1693. Min Act: -0.1700
Data Index: 2676167 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5443. Min Range: -6.5443
Max Act: 6.1693. Min Act: -0.1700
Data Index: 2270261 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5443. Min Range: -6.5443
Max Act: 6.1381. Min Act: -0.1700
Data Index: 3107997 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5443. Min Range: -6.5443
Max Act: 6.1693. Min Act: -0.1700
Data Index: 6907617 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5443. Min Range: -6.5443
Max Act: 6.1068. Min Act: -0.1700
Data Index: 5487568 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5443. Min Range: -6.5443
Max Act: 6.1068. Min Act: -0.1700
Data Index: 176427 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5443. Min Range: -6.5443
Max Act: 6.0443. Min Act: -0.1700
Data Index: 4795329 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5443. Min Range: -6.5443
Max Act: 6.0443. Min Act: -0.1700
Data Index: 7783676 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5443. Min Range: -6.5443
Max Act: 5.9818. Min Act: -0.1700
Data Index: 176447 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5443. Min Range: -6.5443
Max Act: 6.0131. Min Act: -0.1700
Data Index: 6675436 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5443. Min Range: -6.5443
Max Act: 6.0131. Min Act: -0.1700
Data Index: 5622328 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5443. Min Range: -6.5443
Max Act: 5.9193. Min Act: -0.1700
Data Index: 3301043 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19