Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2013 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2188. Min Range: -5.2188
Max Act: 5.2188. Min Act: -0.1700
Data Index: 4820091 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2188. Min Range: -5.2188
Max Act: 5.1563. Min Act: -0.1698
Data Index: 7220069 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2188. Min Range: -5.2188
Max Act: 5.1876. Min Act: -0.1700
Data Index: 5057901 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2188. Min Range: -5.2188
Max Act: 5.1563. Min Act: -0.1700
Data Index: 3915332 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2188. Min Range: -5.2188
Max Act: 5.0938. Min Act: -0.1700
Data Index: 5006123 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2188. Min Range: -5.2188
Max Act: 5.0938. Min Act: -0.1700
Data Index: 2575596 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2188. Min Range: -5.2188
Max Act: 5.0938. Min Act: -0.1700
Data Index: 5548417 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2188. Min Range: -5.2188
Max Act: 5.0938. Min Act: -0.1700
Data Index: 6970982 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2188. Min Range: -5.2188
Max Act: 5.0626. Min Act: -0.1700
Data Index: 2588864 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2188. Min Range: -5.2188
Max Act: 5.0626. Min Act: -0.1700
Data Index: 8727172 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2188. Min Range: -5.2188
Max Act: 5.0626. Min Act: -0.1700
Data Index: 5006122 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2188. Min Range: -5.2188
Max Act: 5.0313. Min Act: -0.1700
Data Index: 3363725 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2188. Min Range: -5.2188
Max Act: 5.0313. Min Act: -0.1700
Data Index: 4506655 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2188. Min Range: -5.2188
Max Act: 5.0313. Min Act: -0.1700
Data Index: 5960176 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2188. Min Range: -5.2188
Max Act: 5.0001. Min Act: -0.1700
Data Index: 1502961 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2188. Min Range: -5.2188
Max Act: 5.0001. Min Act: -0.1700
Data Index: 2435791 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2188. Min Range: -5.2188
Max Act: 5.0001. Min Act: -0.1700
Data Index: 4124919 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2188. Min Range: -5.2188
Max Act: 5.0001. Min Act: -0.1700
Data Index: 131944 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2188. Min Range: -5.2188
Max Act: 5.0001. Min Act: -0.1700
Data Index: 3993767 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2188. Min Range: -5.2188
Max Act: 4.9688. Min Act: -0.1700
Data Index: 5290225 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19