Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2630 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8219. Min Range: -5.8219
Max Act: 5.8219. Min Act: -0.1700
Data Index: 3329405 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8219. Min Range: -5.8219
Max Act: 5.7594. Min Act: -0.1700
Data Index: 4646256 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8219. Min Range: -5.8219
Max Act: 5.6969. Min Act: -0.1700
Data Index: 6328475 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8219. Min Range: -5.8219
Max Act: 5.6344. Min Act: -0.1700
Data Index: 1126347 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8219. Min Range: -5.8219
Max Act: 5.5719. Min Act: -0.1700
Data Index: 2662861 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8219. Min Range: -5.8219
Max Act: 5.5407. Min Act: -0.1700
Data Index: 6350228 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8219. Min Range: -5.8219
Max Act: 5.5407. Min Act: -0.1700
Data Index: 6962344 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8219. Min Range: -5.8219
Max Act: 5.5407. Min Act: -0.1700
Data Index: 5614791 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8219. Min Range: -5.8219
Max Act: 5.4782. Min Act: -0.1700
Data Index: 64700 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8219. Min Range: -5.8219
Max Act: 5.4782. Min Act: -0.1700
Data Index: 888191 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8219. Min Range: -5.8219
Max Act: 5.4469. Min Act: -0.1700
Data Index: 8794951 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8219. Min Range: -5.8219
Max Act: 5.4469. Min Act: -0.1700
Data Index: 4259117 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8219. Min Range: -5.8219
Max Act: 5.4782. Min Act: -0.1700
Data Index: 887071 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8219. Min Range: -5.8219
Max Act: 5.3844. Min Act: -0.1700
Data Index: 2069880 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8219. Min Range: -5.8219
Max Act: 5.4157. Min Act: -0.1700
Data Index: 3647982 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8219. Min Range: -5.8219
Max Act: 5.4469. Min Act: -0.1700
Data Index: 5233671 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8219. Min Range: -5.8219
Max Act: 5.4157. Min Act: -0.1700
Data Index: 710597 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8219. Min Range: -5.8219
Max Act: 5.3844. Min Act: -0.1700
Data Index: 4577571 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8219. Min Range: -5.8219
Max Act: 5.3844. Min Act: -0.1700
Data Index: 1923161 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8219. Min Range: -5.8219
Max Act: 5.3532. Min Act: -0.1700
Data Index: 3829102 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19