Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3511 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.4785. Min Act: -0.1700
Data Index: 1048763 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.4160. Min Act: -0.1700
Data Index: 1699401 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.4472. Min Act: -0.1700
Data Index: 1560000 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.3847. Min Act: -0.1700
Data Index: 8641128 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.4160. Min Act: -0.1700
Data Index: 6595661 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.4160. Min Act: -0.1700
Data Index: 4476811 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.4160. Min Act: -0.1700
Data Index: 1139547 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.3847. Min Act: -0.1700
Data Index: 3297769 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.3847. Min Act: -0.1700
Data Index: 6228043 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.3847. Min Act: -0.1700
Data Index: 531390 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.3847. Min Act: -0.1700
Data Index: 3908789 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.3847. Min Act: -0.1700
Data Index: 3045225 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.3847. Min Act: -0.1700
Data Index: 1962721 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.4160. Min Act: -0.1700
Data Index: 1877221 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.3535. Min Act: -0.1700
Data Index: 3211540 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.3222. Min Act: -0.1700
Data Index: 4762554 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.3535. Min Act: -0.1700
Data Index: 6007734 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.3535. Min Act: -0.1700
Data Index: 4398922 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.3535. Min Act: -0.1700
Data Index: 2917257 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4785. Min Range: -5.4785
Max Act: 5.3535. Min Act: -0.1700
Data Index: 1632904 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19