Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 512 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7268. Min Range: -5.7268
Max Act: 5.7268. Min Act: -0.1700
Data Index: 6632897 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7268. Min Range: -5.7268
Max Act: 5.5393. Min Act: -0.1700
Data Index: 5238075 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7268. Min Range: -5.7268
Max Act: 5.3830. Min Act: -0.1700
Data Index: 2915322 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7268. Min Range: -5.7268
Max Act: 5.3205. Min Act: -0.1700
Data Index: 6023560 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7268. Min Range: -5.7268
Max Act: 5.2893. Min Act: -0.1700
Data Index: 2094338 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7268. Min Range: -5.7268
Max Act: 5.2893. Min Act: -0.1700
Data Index: 1014907 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7268. Min Range: -5.7268
Max Act: 5.2580. Min Act: -0.1700
Data Index: 2308623 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7268. Min Range: -5.7268
Max Act: 5.2580. Min Act: -0.1700
Data Index: 6102124 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7268. Min Range: -5.7268
Max Act: 5.2268. Min Act: -0.1700
Data Index: 1658637 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7268. Min Range: -5.7268
Max Act: 5.1955. Min Act: -0.1700
Data Index: 3850234 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7268. Min Range: -5.7268
Max Act: 5.1330. Min Act: -0.1700
Data Index: 2338780 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7268. Min Range: -5.7268
Max Act: 5.1643. Min Act: -0.1700
Data Index: 4167139 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7268. Min Range: -5.7268
Max Act: 5.1018. Min Act: -0.1700
Data Index: 5403732 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7268. Min Range: -5.7268
Max Act: 5.1330. Min Act: -0.1700
Data Index: 1636902 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7268. Min Range: -5.7268
Max Act: 5.1330. Min Act: -0.1700
Data Index: 8725333 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7268. Min Range: -5.7268
Max Act: 5.1330. Min Act: -0.1700
Data Index: 4597886 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7268. Min Range: -5.7268
Max Act: 5.1643. Min Act: -0.1700
Data Index: 5210026 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7268. Min Range: -5.7268
Max Act: 5.1018. Min Act: -0.1700
Data Index: 5773956 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7268. Min Range: -5.7268
Max Act: 5.1330. Min Act: -0.1700
Data Index: 8111357 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7268. Min Range: -5.7268
Max Act: 5.1018. Min Act: -0.1700
Data Index: 2443651 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19