Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.4342. Min Act: -0.1700
Data Index: 7407406 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.3717. Min Act: -0.1700
Data Index: 7156976 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.2779. Min Act: -0.1700
Data Index: 4387554 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.2467. Min Act: -0.1700
Data Index: 2127585 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.2154. Min Act: -0.1700
Data Index: 4100598 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.1842. Min Act: -0.1700
Data Index: 4725960 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.1217. Min Act: -0.1700
Data Index: 7770161 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.0592. Min Act: -0.1700
Data Index: 1725502 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.0592. Min Act: -0.1700
Data Index: 2801859 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.0904. Min Act: -0.1700
Data Index: 2554351 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.0592. Min Act: -0.1700
Data Index: 5355304 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.0279. Min Act: -0.1700
Data Index: 8700888 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.0904. Min Act: -0.1700
Data Index: 3271243 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.0592. Min Act: -0.1700
Data Index: 6485999 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.0592. Min Act: -0.1700
Data Index: 2889692 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.0592. Min Act: -0.1700
Data Index: 3193504 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.0592. Min Act: -0.1700
Data Index: 5672325 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.0279. Min Act: -0.1700
Data Index: 2516626 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4342. Min Range: -5.4342
Max Act: 5.0279. Min Act: -0.1700
Data Index: 8642811 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4342. Min Range: -5.4342
Max Act: 4.9967. Min Act: -0.1700
Data Index: 4648821 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19