Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 993 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1235. Min Range: -4.1235
Max Act: 4.1235. Min Act: -0.1700
Data Index: 6028760 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.9985. Min Act: -0.1700
Data Index: 6529520 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.9673. Min Act: -0.1700
Data Index: 3252504 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.9673. Min Act: -0.1700
Data Index: 5547056 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.9360. Min Act: -0.1700
Data Index: 1094652 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.9360. Min Act: -0.1700
Data Index: 6916270 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.9360. Min Act: -0.1700
Data Index: 2699637 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.8735. Min Act: -0.1700
Data Index: 929087 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.8422. Min Act: -0.1700
Data Index: 6861844 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.8735. Min Act: -0.1700
Data Index: 2744602 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.8109. Min Act: -0.1700
Data Index: 3876609 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.8422. Min Act: -0.1700
Data Index: 7690309 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.8266. Min Act: -0.1700
Data Index: 1825697 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.8422. Min Act: -0.1700
Data Index: 3643679 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.8266. Min Act: -0.1700
Data Index: 2160702 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.8109. Min Act: -0.1700
Data Index: 672116 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.8266. Min Act: -0.1700
Data Index: 6103264 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.8109. Min Act: -0.1700
Data Index: 5035261 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.8109. Min Act: -0.1700
Data Index: 5260479 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.7640. Min Act: -0.1700
Data Index: 5438513 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19