Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3068 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2928. Min Range: -5.2928
Max Act: 5.2928. Min Act: -0.1700
Data Index: 6219701 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2928. Min Range: -5.2928
Max Act: 5.0116. Min Act: -0.1700
Data Index: 5621071 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2928. Min Range: -5.2928
Max Act: 5.0116. Min Act: -0.1700
Data Index: 648841 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2928. Min Range: -5.2928
Max Act: 5.0116. Min Act: -0.1700
Data Index: 5265466 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2928. Min Range: -5.2928
Max Act: 4.9491. Min Act: -0.1700
Data Index: 3591222 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2928. Min Range: -5.2928
Max Act: 4.9178. Min Act: -0.1700
Data Index: 4542423 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2928. Min Range: -5.2928
Max Act: 4.9491. Min Act: -0.1700
Data Index: 7004170 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2928. Min Range: -5.2928
Max Act: 4.8866. Min Act: -0.1700
Data Index: 1828909 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2928. Min Range: -5.2928
Max Act: 4.8866. Min Act: -0.1700
Data Index: 3886351 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2928. Min Range: -5.2928
Max Act: 4.8866. Min Act: -0.1700
Data Index: 4745258 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2928. Min Range: -5.2928
Max Act: 4.8866. Min Act: -0.1700
Data Index: 4680602 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2928. Min Range: -5.2928
Max Act: 4.8553. Min Act: -0.1700
Data Index: 6350074 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2928. Min Range: -5.2928
Max Act: 4.8553. Min Act: -0.1700
Data Index: 4666636 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2928. Min Range: -5.2928
Max Act: 4.8553. Min Act: -0.1700
Data Index: 1493673 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2928. Min Range: -5.2928
Max Act: 4.8241. Min Act: -0.1700
Data Index: 2051189 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2928. Min Range: -5.2928
Max Act: 4.8241. Min Act: -0.1700
Data Index: 4055869 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2928. Min Range: -5.2928
Max Act: 4.8241. Min Act: -0.1700
Data Index: 6763615 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2928. Min Range: -5.2928
Max Act: 4.7928. Min Act: -0.1700
Data Index: 6991140 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2928. Min Range: -5.2928
Max Act: 4.8241. Min Act: -0.1700
Data Index: 1127345 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2928. Min Range: -5.2928
Max Act: 4.8241. Min Act: -0.1700
Data Index: 5600962 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19