Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3499 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3449. Min Range: -5.3449
Max Act: 5.3449. Min Act: -0.1700
Data Index: 5401223 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3449. Min Range: -5.3449
Max Act: 5.3137. Min Act: -0.1700
Data Index: 6330013 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3449. Min Range: -5.3449
Max Act: 5.2199. Min Act: -0.1700
Data Index: 4010580 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3449. Min Range: -5.3449
Max Act: 5.2512. Min Act: -0.1700
Data Index: 1023632 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3449. Min Range: -5.3449
Max Act: 5.2512. Min Act: -0.1700
Data Index: 7296691 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3449. Min Range: -5.3449
Max Act: 5.2512. Min Act: -0.1700
Data Index: 3239401 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3449. Min Range: -5.3449
Max Act: 5.2512. Min Act: -0.1700
Data Index: 5159571 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3449. Min Range: -5.3449
Max Act: 5.1887. Min Act: -0.1700
Data Index: 6392495 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3449. Min Range: -5.3449
Max Act: 5.2199. Min Act: -0.1700
Data Index: 7185685 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3449. Min Range: -5.3449
Max Act: 5.2199. Min Act: -0.1700
Data Index: 7662874 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3449. Min Range: -5.3449
Max Act: 5.2199. Min Act: -0.1700
Data Index: 3820273 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3449. Min Range: -5.3449
Max Act: 5.2199. Min Act: -0.1700
Data Index: 3919444 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3449. Min Range: -5.3449
Max Act: 5.1887. Min Act: -0.1700
Data Index: 3888746 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3449. Min Range: -5.3449
Max Act: 5.1887. Min Act: -0.1700
Data Index: 8728001 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3449. Min Range: -5.3449
Max Act: 5.1887. Min Act: -0.1700
Data Index: 7948177 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3449. Min Range: -5.3449
Max Act: 5.1887. Min Act: -0.1700
Data Index: 3449135 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3449. Min Range: -5.3449
Max Act: 5.1887. Min Act: -0.1700
Data Index: 5817154 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3449. Min Range: -5.3449
Max Act: 5.1887. Min Act: -0.1700
Data Index: 4948776 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3449. Min Range: -5.3449
Max Act: 5.1262. Min Act: -0.1700
Data Index: 1915189 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3449. Min Range: -5.3449
Max Act: 5.1574. Min Act: -0.1700
Data Index: 629831 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19