Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3696 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9255. Min Range: -3.9255
Max Act: 3.9255. Min Act: -0.1700
Data Index: 344359 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9255. Min Range: -3.9255
Max Act: 3.8943. Min Act: -0.1700
Data Index: 318823 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9255. Min Range: -3.9255
Max Act: 3.8317. Min Act: -0.1700
Data Index: 3090862 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9255. Min Range: -3.9255
Max Act: 3.7536. Min Act: -0.1700
Data Index: 8293497 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9255. Min Range: -3.9255
Max Act: 3.7692. Min Act: -0.1700
Data Index: 5339912 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9255. Min Range: -3.9255
Max Act: 3.7379. Min Act: -0.1700
Data Index: 8565438 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9255. Min Range: -3.9255
Max Act: 3.7223. Min Act: -0.1700
Data Index: 5476325 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9255. Min Range: -3.9255
Max Act: 3.7066. Min Act: -0.1700
Data Index: 749407 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9255. Min Range: -3.9255
Max Act: 3.6753. Min Act: -0.1700
Data Index: 3406152 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9255. Min Range: -3.9255
Max Act: 3.6910. Min Act: -0.1700
Data Index: 1821324 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9255. Min Range: -3.9255
Max Act: 3.6597. Min Act: -0.1700
Data Index: 5830044 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9255. Min Range: -3.9255
Max Act: 3.6597. Min Act: -0.1700
Data Index: 2671362 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9255. Min Range: -3.9255
Max Act: 3.6597. Min Act: -0.1700
Data Index: 7975586 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9255. Min Range: -3.9255
Max Act: 3.6597. Min Act: -0.1700
Data Index: 7716550 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9255. Min Range: -3.9255
Max Act: 3.6441. Min Act: -0.1700
Data Index: 210057 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9255. Min Range: -3.9255
Max Act: 3.6597. Min Act: -0.1700
Data Index: 8224952 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9255. Min Range: -3.9255
Max Act: 3.6441. Min Act: -0.1700
Data Index: 8408971 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9255. Min Range: -3.9255
Max Act: 3.6284. Min Act: -0.1700
Data Index: 3407134 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9255. Min Range: -3.9255
Max Act: 3.6284. Min Act: -0.1700
Data Index: 1567497 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9255. Min Range: -3.9255
Max Act: 3.6284. Min Act: -0.1700
Data Index: 2301090 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19