Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5404 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1083. Min Range: -4.1083
Max Act: 4.1083. Min Act: -0.1700
Data Index: 3716724 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1083. Min Range: -4.1083
Max Act: 3.9520. Min Act: -0.1700
Data Index: 7824220 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1083. Min Range: -4.1083
Max Act: 3.8582. Min Act: -0.1700
Data Index: 2651497 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1083. Min Range: -4.1083
Max Act: 3.8894. Min Act: -0.1700
Data Index: 5369181 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1083. Min Range: -4.1083
Max Act: 3.8269. Min Act: -0.1700
Data Index: 2255455 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1083. Min Range: -4.1083
Max Act: 3.8269. Min Act: -0.1700
Data Index: 7052151 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1083. Min Range: -4.1083
Max Act: 3.7956. Min Act: -0.1700
Data Index: 3451119 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1083. Min Range: -4.1083
Max Act: 3.7956. Min Act: -0.1700
Data Index: 3123312 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1083. Min Range: -4.1083
Max Act: 3.7956. Min Act: -0.1700
Data Index: 3731933 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1083. Min Range: -4.1083
Max Act: 3.7956. Min Act: -0.1700
Data Index: 6740166 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1083. Min Range: -4.1083
Max Act: 3.7643. Min Act: -0.1700
Data Index: 4452116 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1083. Min Range: -4.1083
Max Act: 3.7643. Min Act: -0.1700
Data Index: 6398459 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1083. Min Range: -4.1083
Max Act: 3.7643. Min Act: -0.1700
Data Index: 5131441 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1083. Min Range: -4.1083
Max Act: 3.7643. Min Act: -0.1700
Data Index: 4092482 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1083. Min Range: -4.1083
Max Act: 3.7331. Min Act: -0.1700
Data Index: 694714 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1083. Min Range: -4.1083
Max Act: 3.7331. Min Act: -0.1700
Data Index: 1313753 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1083. Min Range: -4.1083
Max Act: 3.7331. Min Act: -0.1700
Data Index: 3033994 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1083. Min Range: -4.1083
Max Act: 3.7331. Min Act: -0.1700
Data Index: 4408934 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1083. Min Range: -4.1083
Max Act: 3.7331. Min Act: -0.1700
Data Index: 4044537 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1083. Min Range: -4.1083
Max Act: 3.7331. Min Act: -0.1700
Data Index: 8030949 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19