Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 160 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6823. Min Range: -1.6823
Max Act: 1.6823. Min Act: -0.1700
Data Index: 6842994 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6823. Min Range: -1.6823
Max Act: 1.5076. Min Act: -0.1700
Data Index: 5023666 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6823. Min Range: -1.6823
Max Act: 1.4989. Min Act: -0.1700
Data Index: 2545360 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6823. Min Range: -1.6823
Max Act: 1.4989. Min Act: -0.1700
Data Index: 4056576 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6823. Min Range: -1.6823
Max Act: 1.4813. Min Act: -0.1700
Data Index: 8600264 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6823. Min Range: -1.6823
Max Act: 1.4725. Min Act: -0.1700
Data Index: 4543572 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6823. Min Range: -1.6823
Max Act: 1.4637. Min Act: -0.1700
Data Index: 6671818 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6823. Min Range: -1.6823
Max Act: 1.4637. Min Act: -0.1700
Data Index: 3541994 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6823. Min Range: -1.6823
Max Act: 1.4549. Min Act: -0.1700
Data Index: 6509816 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6823. Min Range: -1.6823
Max Act: 1.4549. Min Act: -0.1700
Data Index: 7769862 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6823. Min Range: -1.6823
Max Act: 1.4461. Min Act: -0.1700
Data Index: 5770284 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6823. Min Range: -1.6823
Max Act: 1.4285. Min Act: -0.1700
Data Index: 4341210 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6823. Min Range: -1.6823
Max Act: 1.4373. Min Act: -0.1700
Data Index: 3420882 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6823. Min Range: -1.6823
Max Act: 1.4373. Min Act: -0.1700
Data Index: 593379 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6823. Min Range: -1.6823
Max Act: 1.4285. Min Act: -0.1700
Data Index: 5680226 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6823. Min Range: -1.6823
Max Act: 1.4285. Min Act: -0.1700
Data Index: 5683958 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6823. Min Range: -1.6823
Max Act: 1.4197. Min Act: -0.1700
Data Index: 6134263 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6823. Min Range: -1.6823
Max Act: 1.4021. Min Act: -0.1700
Data Index: 5484391 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6823. Min Range: -1.6823
Max Act: 1.4109. Min Act: -0.1700
Data Index: 1161846 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6823. Min Range: -1.6823
Max Act: 1.4021. Min Act: -0.1700
Data Index: 6730842 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19