Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3285 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2124. Min Range: -7.2124
Max Act: 7.2124. Min Act: -0.1700
Data Index: 6047575 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2124. Min Range: -7.2124
Max Act: 6.7749. Min Act: -0.1700
Data Index: 3117162 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2124. Min Range: -7.2124
Max Act: 6.7749. Min Act: -0.1700
Data Index: 6089049 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2124. Min Range: -7.2124
Max Act: 6.7436. Min Act: -0.1700
Data Index: 8654262 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2124. Min Range: -7.2124
Max Act: 6.7436. Min Act: -0.1700
Data Index: 7428741 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2124. Min Range: -7.2124
Max Act: 6.6811. Min Act: -0.1700
Data Index: 5993938 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2124. Min Range: -7.2124
Max Act: 6.6186. Min Act: -0.1700
Data Index: 5242141 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2124. Min Range: -7.2124
Max Act: 6.6499. Min Act: -0.1700
Data Index: 6760849 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2124. Min Range: -7.2124
Max Act: 6.6186. Min Act: -0.1700
Data Index: 7111914 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2124. Min Range: -7.2124
Max Act: 6.5249. Min Act: -0.1700
Data Index: 1006607 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2124. Min Range: -7.2124
Max Act: 6.5249. Min Act: -0.1700
Data Index: 5791883 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2124. Min Range: -7.2124
Max Act: 6.4936. Min Act: -0.1700
Data Index: 2300875 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2124. Min Range: -7.2124
Max Act: 6.4936. Min Act: -0.1700
Data Index: 7473946 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2124. Min Range: -7.2124
Max Act: 6.4936. Min Act: -0.1700
Data Index: 1531349 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2124. Min Range: -7.2124
Max Act: 6.4624. Min Act: -0.1700
Data Index: 5856434 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2124. Min Range: -7.2124
Max Act: 6.4624. Min Act: -0.1700
Data Index: 8038759 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2124. Min Range: -7.2124
Max Act: 6.4311. Min Act: -0.1700
Data Index: 6782785 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2124. Min Range: -7.2124
Max Act: 6.4311. Min Act: -0.1700
Data Index: 6893163 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2124. Min Range: -7.2124
Max Act: 6.3686. Min Act: -0.1700
Data Index: 6153583 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2124. Min Range: -7.2124
Max Act: 6.3374. Min Act: -0.1700
Data Index: 4414696 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19