Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2898 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6660. Min Range: -5.6660
Max Act: 5.6660. Min Act: -0.1700
Data Index: 1949147 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6660. Min Range: -5.6660
Max Act: 5.5098. Min Act: -0.1700
Data Index: 3968267 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6660. Min Range: -5.6660
Max Act: 5.5098. Min Act: -0.1700
Data Index: 9051 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6660. Min Range: -5.6660
Max Act: 5.4785. Min Act: -0.1700
Data Index: 5624521 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6660. Min Range: -5.6660
Max Act: 5.4160. Min Act: -0.1700
Data Index: 5457935 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6660. Min Range: -5.6660
Max Act: 5.3535. Min Act: -0.1700
Data Index: 6057901 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6660. Min Range: -5.6660
Max Act: 5.2910. Min Act: -0.1700
Data Index: 7289677 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6660. Min Range: -5.6660
Max Act: 5.2910. Min Act: -0.1700
Data Index: 5469409 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6660. Min Range: -5.6660
Max Act: 5.2910. Min Act: -0.1700
Data Index: 7964513 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6660. Min Range: -5.6660
Max Act: 5.2910. Min Act: -0.1700
Data Index: 6831194 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6660. Min Range: -5.6660
Max Act: 5.2598. Min Act: -0.1700
Data Index: 1253347 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6660. Min Range: -5.6660
Max Act: 5.2910. Min Act: -0.1700
Data Index: 6540032 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6660. Min Range: -5.6660
Max Act: 5.2598. Min Act: -0.1700
Data Index: 7465535 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6660. Min Range: -5.6660
Max Act: 5.2285. Min Act: -0.1700
Data Index: 2068598 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6660. Min Range: -5.6660
Max Act: 5.2285. Min Act: -0.1700
Data Index: 7609238 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6660. Min Range: -5.6660
Max Act: 5.2285. Min Act: -0.1700
Data Index: 3401082 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6660. Min Range: -5.6660
Max Act: 5.2285. Min Act: -0.1700
Data Index: 2493312 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6660. Min Range: -5.6660
Max Act: 5.1973. Min Act: -0.1700
Data Index: 6390170 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6660. Min Range: -5.6660
Max Act: 5.1973. Min Act: -0.1700
Data Index: 1783572 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6660. Min Range: -5.6660
Max Act: 5.1660. Min Act: -0.1700
Data Index: 2680880 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19