Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3500 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2851. Min Range: -7.2851
Max Act: 7.2851. Min Act: -0.1700
Data Index: 1622899 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2851. Min Range: -7.2851
Max Act: 7.2539. Min Act: -0.1700
Data Index: 8157443 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2851. Min Range: -7.2851
Max Act: 7.2539. Min Act: -0.1700
Data Index: 5699195 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2851. Min Range: -7.2851
Max Act: 7.1914. Min Act: -0.1700
Data Index: 4688076 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2851. Min Range: -7.2851
Max Act: 7.1601. Min Act: -0.1700
Data Index: 4299552 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2851. Min Range: -7.2851
Max Act: 7.1289. Min Act: -0.1700
Data Index: 5908230 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2851. Min Range: -7.2851
Max Act: 7.1289. Min Act: -0.1700
Data Index: 281604 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2851. Min Range: -7.2851
Max Act: 7.0976. Min Act: -0.1700
Data Index: 7731151 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2851. Min Range: -7.2851
Max Act: 7.0664. Min Act: -0.1700
Data Index: 937320 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2851. Min Range: -7.2851
Max Act: 7.0039. Min Act: -0.1700
Data Index: 1597980 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2851. Min Range: -7.2851
Max Act: 6.9726. Min Act: -0.1700
Data Index: 6468202 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2851. Min Range: -7.2851
Max Act: 7.0039. Min Act: -0.1700
Data Index: 2122801 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2851. Min Range: -7.2851
Max Act: 6.9726. Min Act: -0.1700
Data Index: 7686105 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2851. Min Range: -7.2851
Max Act: 6.9414. Min Act: -0.1700
Data Index: 7029022 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2851. Min Range: -7.2851
Max Act: 6.9101. Min Act: -0.1700
Data Index: 1635019 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2851. Min Range: -7.2851
Max Act: 6.9101. Min Act: -0.1700
Data Index: 3991242 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2851. Min Range: -7.2851
Max Act: 6.8476. Min Act: -0.1700
Data Index: 100053 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2851. Min Range: -7.2851
Max Act: 6.8789. Min Act: -0.1700
Data Index: 1263906 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2851. Min Range: -7.2851
Max Act: 6.8476. Min Act: -0.1700
Data Index: 5630822 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2851. Min Range: -7.2851
Max Act: 6.8476. Min Act: -0.1700
Data Index: 5743334 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19