Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3924 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.3074. Min Act: -0.1700
Data Index: 6940304 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.2762. Min Act: -0.1700
Data Index: 3770100 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.2762. Min Act: -0.1700
Data Index: 3265413 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.2449. Min Act: -0.1700
Data Index: 1295720 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.2449. Min Act: -0.1700
Data Index: 1327765 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.2137. Min Act: -0.1700
Data Index: 7923331 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.2137. Min Act: -0.1700
Data Index: 3650335 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1824. Min Act: -0.1700
Data Index: 1831518 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1512. Min Act: -0.1700
Data Index: 4244661 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1512. Min Act: -0.1700
Data Index: 7593079 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1512. Min Act: -0.1700
Data Index: 6154759 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1824. Min Act: -0.1700
Data Index: 3316115 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1512. Min Act: -0.1700
Data Index: 2786884 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1512. Min Act: -0.1700
Data Index: 4801017 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.0887. Min Act: -0.1700
Data Index: 438513 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.1199. Min Act: -0.1700
Data Index: 3941156 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.0887. Min Act: -0.1700
Data Index: 550889 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.0574. Min Act: -0.1700
Data Index: 2209000 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.0887. Min Act: -0.1700
Data Index: 4519629 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.0574. Min Act: -0.1700
Data Index: 1539510 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19