Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 741 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1842. Min Range: -6.1842
Max Act: 6.1842. Min Act: -0.1700
Data Index: 5225471 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1842. Min Range: -6.1842
Max Act: 6.0905. Min Act: -0.1700
Data Index: 7398686 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1842. Min Range: -6.1842
Max Act: 6.0592. Min Act: -0.1700
Data Index: 2246036 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1842. Min Range: -6.1842
Max Act: 6.0592. Min Act: -0.1700
Data Index: 3823849 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1842. Min Range: -6.1842
Max Act: 6.0592. Min Act: -0.1700
Data Index: 5209117 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1842. Min Range: -6.1842
Max Act: 6.0280. Min Act: -0.1700
Data Index: 73861 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1842. Min Range: -6.1842
Max Act: 6.0280. Min Act: -0.1700
Data Index: 456419 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1842. Min Range: -6.1842
Max Act: 5.9967. Min Act: -0.1700
Data Index: 571853 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1842. Min Range: -6.1842
Max Act: 5.9967. Min Act: -0.1700
Data Index: 8002862 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1842. Min Range: -6.1842
Max Act: 5.9655. Min Act: -0.1700
Data Index: 7379745 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1842. Min Range: -6.1842
Max Act: 5.9967. Min Act: -0.1700
Data Index: 3146807 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1842. Min Range: -6.1842
Max Act: 5.9655. Min Act: -0.1700
Data Index: 4333327 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1842. Min Range: -6.1842
Max Act: 5.9342. Min Act: -0.1700
Data Index: 5021368 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1842. Min Range: -6.1842
Max Act: 5.9342. Min Act: -0.1700
Data Index: 4744842 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1842. Min Range: -6.1842
Max Act: 5.9342. Min Act: -0.1700
Data Index: 7791960 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1842. Min Range: -6.1842
Max Act: 5.9030. Min Act: -0.1700
Data Index: 5235424 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1842. Min Range: -6.1842
Max Act: 5.9342. Min Act: -0.1700
Data Index: 428409 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1842. Min Range: -6.1842
Max Act: 5.9342. Min Act: -0.1700
Data Index: 5163177 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1842. Min Range: -6.1842
Max Act: 5.9342. Min Act: -0.1700
Data Index: 3118751 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1842. Min Range: -6.1842
Max Act: 5.9342. Min Act: -0.1700
Data Index: 7702284 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19