Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2055 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1255. Min Range: -5.1255
Max Act: 5.1255. Min Act: -0.1700
Data Index: 8531665 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1255. Min Range: -5.1255
Max Act: 5.0630. Min Act: -0.1700
Data Index: 4700619 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1255. Min Range: -5.1255
Max Act: 4.8755. Min Act: -0.1700
Data Index: 4291041 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1255. Min Range: -5.1255
Max Act: 4.8442. Min Act: -0.1700
Data Index: 1071855 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1255. Min Range: -5.1255
Max Act: 4.8442. Min Act: -0.1700
Data Index: 4356506 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1255. Min Range: -5.1255
Max Act: 4.8130. Min Act: -0.1700
Data Index: 7678430 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1255. Min Range: -5.1255
Max Act: 4.7817. Min Act: -0.1700
Data Index: 8137119 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1255. Min Range: -5.1255
Max Act: 4.7505. Min Act: -0.1700
Data Index: 1921638 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1255. Min Range: -5.1255
Max Act: 4.7192. Min Act: -0.1700
Data Index: 6354021 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1255. Min Range: -5.1255
Max Act: 4.7192. Min Act: -0.1700
Data Index: 249890 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1255. Min Range: -5.1255
Max Act: 4.7192. Min Act: -0.1700
Data Index: 4662605 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1255. Min Range: -5.1255
Max Act: 4.6880. Min Act: -0.1700
Data Index: 7904151 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1255. Min Range: -5.1255
Max Act: 4.6880. Min Act: -0.1700
Data Index: 1391439 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1255. Min Range: -5.1255
Max Act: 4.7192. Min Act: -0.1700
Data Index: 847040 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1255. Min Range: -5.1255
Max Act: 4.6880. Min Act: -0.1700
Data Index: 3117084 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1255. Min Range: -5.1255
Max Act: 4.6880. Min Act: -0.1700
Data Index: 1157364 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1255. Min Range: -5.1255
Max Act: 4.6255. Min Act: -0.1700
Data Index: 3899520 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1255. Min Range: -5.1255
Max Act: 4.6255. Min Act: -0.1700
Data Index: 4671160 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1255. Min Range: -5.1255
Max Act: 4.6255. Min Act: -0.1700
Data Index: 4297119 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1255. Min Range: -5.1255
Max Act: 4.6255. Min Act: -0.1700
Data Index: 2543141 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19