Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1954 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9527. Min Range: -5.9527
Max Act: 5.9527. Min Act: -0.1700
Data Index: 5954711 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9527. Min Range: -5.9527
Max Act: 5.8902. Min Act: -0.1700
Data Index: 4654537 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9527. Min Range: -5.9527
Max Act: 5.8277. Min Act: -0.1700
Data Index: 904469 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9527. Min Range: -5.9527
Max Act: 5.8277. Min Act: -0.1700
Data Index: 998594 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9527. Min Range: -5.9527
Max Act: 5.7652. Min Act: -0.1700
Data Index: 3717718 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9527. Min Range: -5.9527
Max Act: 5.7964. Min Act: -0.1700
Data Index: 3442061 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9527. Min Range: -5.9527
Max Act: 5.8277. Min Act: -0.1700
Data Index: 4995879 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9527. Min Range: -5.9527
Max Act: 5.7964. Min Act: -0.1700
Data Index: 979813 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9527. Min Range: -5.9527
Max Act: 5.7964. Min Act: -0.1700
Data Index: 1632372 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9527. Min Range: -5.9527
Max Act: 5.7964. Min Act: -0.1700
Data Index: 3743091 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9527. Min Range: -5.9527
Max Act: 5.7652. Min Act: -0.1700
Data Index: 5266340 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9527. Min Range: -5.9527
Max Act: 5.7652. Min Act: -0.1700
Data Index: 6243456 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9527. Min Range: -5.9527
Max Act: 5.7652. Min Act: -0.1700
Data Index: 6516000 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9527. Min Range: -5.9527
Max Act: 5.7652. Min Act: -0.1700
Data Index: 3419572 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9527. Min Range: -5.9527
Max Act: 5.7652. Min Act: -0.1700
Data Index: 3859011 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9527. Min Range: -5.9527
Max Act: 5.7339. Min Act: -0.1700
Data Index: 3776105 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9527. Min Range: -5.9527
Max Act: 5.7027. Min Act: -0.1700
Data Index: 1475543 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9527. Min Range: -5.9527
Max Act: 5.7027. Min Act: -0.1700
Data Index: 666050 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9527. Min Range: -5.9527
Max Act: 5.7027. Min Act: -0.1700
Data Index: 3377145 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9527. Min Range: -5.9527
Max Act: 5.7027. Min Act: -0.1700
Data Index: 105889 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19