Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1568 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.6638. Min Act: -0.1700
Data Index: 2736395 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.5189. Min Act: -0.1700
Data Index: 6379821 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.5027. Min Act: -0.1700
Data Index: 1324390 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.4865. Min Act: -0.1700
Data Index: 2576161 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.4702. Min Act: -0.1700
Data Index: 3050808 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.4865. Min Act: -0.1700
Data Index: 1885018 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.4702. Min Act: -0.1700
Data Index: 7033828 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.4702. Min Act: -0.1700
Data Index: 493527 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.4540. Min Act: -0.1700
Data Index: 7744743 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.4377. Min Act: -0.1700
Data Index: 2576160 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.4377. Min Act: -0.1700
Data Index: 4630714 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.4377. Min Act: -0.1700
Data Index: 5376969 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.4377. Min Act: -0.1700
Data Index: 8073261 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.4377. Min Act: -0.1700
Data Index: 4313854 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.4214. Min Act: -0.1700
Data Index: 6680343 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.4214. Min Act: -0.1700
Data Index: 6680342 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.4214. Min Act: -0.1700
Data Index: 4614753 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.4214. Min Act: -0.1700
Data Index: 8821294 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.4214. Min Act: -0.1700
Data Index: 894891 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6638. Min Range: -2.6638
Max Act: 2.4051. Min Act: -0.1700
Data Index: 391396 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19