Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4040 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5332. Min Range: -5.5332
Max Act: 5.5332. Min Act: -0.1700
Data Index: 3538558 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5332. Min Range: -5.5332
Max Act: 5.3144. Min Act: -0.1700
Data Index: 5983059 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5332. Min Range: -5.5332
Max Act: 5.2207. Min Act: -0.1700
Data Index: 2121513 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5332. Min Range: -5.5332
Max Act: 5.2207. Min Act: -0.1700
Data Index: 2732094 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5332. Min Range: -5.5332
Max Act: 5.1894. Min Act: -0.1700
Data Index: 5151322 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5332. Min Range: -5.5332
Max Act: 5.1894. Min Act: -0.1700
Data Index: 3647360 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5332. Min Range: -5.5332
Max Act: 5.1582. Min Act: -0.1700
Data Index: 7041594 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5332. Min Range: -5.5332
Max Act: 5.1582. Min Act: -0.1700
Data Index: 7510179 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5332. Min Range: -5.5332
Max Act: 5.1269. Min Act: -0.1700
Data Index: 3647345 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5332. Min Range: -5.5332
Max Act: 5.0957. Min Act: -0.1700
Data Index: 2479789 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5332. Min Range: -5.5332
Max Act: 5.0957. Min Act: -0.1700
Data Index: 1806960 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5332. Min Range: -5.5332
Max Act: 5.0644. Min Act: -0.1700
Data Index: 7149924 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5332. Min Range: -5.5332
Max Act: 5.0644. Min Act: -0.1700
Data Index: 7394854 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5332. Min Range: -5.5332
Max Act: 5.0332. Min Act: -0.1700
Data Index: 6478290 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5332. Min Range: -5.5332
Max Act: 5.0019. Min Act: -0.1700
Data Index: 7516088 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5332. Min Range: -5.5332
Max Act: 4.9707. Min Act: -0.1700
Data Index: 4175909 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5332. Min Range: -5.5332
Max Act: 4.9394. Min Act: -0.1700
Data Index: 629781 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5332. Min Range: -5.5332
Max Act: 4.9707. Min Act: -0.1700
Data Index: 2192114 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5332. Min Range: -5.5332
Max Act: 5.0019. Min Act: -0.1700
Data Index: 3427914 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5332. Min Range: -5.5332
Max Act: 4.9707. Min Act: -0.1700
Data Index: 2313770 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19