Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3497 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8234. Min Range: -3.8234
Max Act: 3.8234. Min Act: -0.1700
Data Index: 3768182 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8234. Min Range: -3.8234
Max Act: 3.8234. Min Act: -0.1700
Data Index: 7884569 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8234. Min Range: -3.8234
Max Act: 3.7921. Min Act: -0.1700
Data Index: 4546112 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8234. Min Range: -3.8234
Max Act: 3.7921. Min Act: -0.1700
Data Index: 165338 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8234. Min Range: -3.8234
Max Act: 3.7608. Min Act: -0.1700
Data Index: 800917 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8234. Min Range: -3.8234
Max Act: 3.7295. Min Act: -0.1700
Data Index: 6651931 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8234. Min Range: -3.8234
Max Act: 3.7295. Min Act: -0.1700
Data Index: 461217 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8234. Min Range: -3.8234
Max Act: 3.6982. Min Act: -0.1700
Data Index: 3654173 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8234. Min Range: -3.8234
Max Act: 3.7295. Min Act: -0.1700
Data Index: 1460311 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8234. Min Range: -3.8234
Max Act: 3.7295. Min Act: -0.1700
Data Index: 7884568 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8234. Min Range: -3.8234
Max Act: 3.7295. Min Act: -0.1700
Data Index: 257146 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8234. Min Range: -3.8234
Max Act: 3.7295. Min Act: -0.1700
Data Index: 7499872 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8234. Min Range: -3.8234
Max Act: 3.7295. Min Act: -0.1700
Data Index: 6809755 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8234. Min Range: -3.8234
Max Act: 3.7295. Min Act: -0.1700
Data Index: 984529 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8234. Min Range: -3.8234
Max Act: 3.6670. Min Act: -0.1700
Data Index: 1815341 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8234. Min Range: -3.8234
Max Act: 3.6982. Min Act: -0.1700
Data Index: 317230 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8234. Min Range: -3.8234
Max Act: 3.6982. Min Act: -0.1700
Data Index: 3702269 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8234. Min Range: -3.8234
Max Act: 3.6982. Min Act: -0.1700
Data Index: 1056424 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8234. Min Range: -3.8234
Max Act: 3.6982. Min Act: -0.1700
Data Index: 6719913 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8234. Min Range: -3.8234
Max Act: 3.6982. Min Act: -0.1700
Data Index: 830892 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19