Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3798 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5888. Min Range: -6.5888
Max Act: 6.5888. Min Act: -0.1700
Data Index: 7789061 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5888. Min Range: -6.5888
Max Act: 6.5888. Min Act: -0.1700
Data Index: 7789076 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5888. Min Range: -6.5888
Max Act: 6.5263. Min Act: -0.1700
Data Index: 3848324 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5888. Min Range: -6.5888
Max Act: 6.5263. Min Act: -0.1700
Data Index: 7789078 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5888. Min Range: -6.5888
Max Act: 6.5576. Min Act: -0.1700
Data Index: 5317457 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5888. Min Range: -6.5888
Max Act: 6.4951. Min Act: -0.1700
Data Index: 3612067 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5888. Min Range: -6.5888
Max Act: 6.4638. Min Act: -0.1700
Data Index: 7789075 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5888. Min Range: -6.5888
Max Act: 6.4326. Min Act: -0.1700
Data Index: 6754505 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5888. Min Range: -6.5888
Max Act: 6.4638. Min Act: -0.1700
Data Index: 7789079 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5888. Min Range: -6.5888
Max Act: 6.4326. Min Act: -0.1700
Data Index: 7789081 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5888. Min Range: -6.5888
Max Act: 6.4013. Min Act: -0.1700
Data Index: 8369400 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5888. Min Range: -6.5888
Max Act: 6.4013. Min Act: -0.1700
Data Index: 7789074 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5888. Min Range: -6.5888
Max Act: 6.3701. Min Act: -0.1700
Data Index: 3612068 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5888. Min Range: -6.5888
Max Act: 6.3701. Min Act: -0.1700
Data Index: 709087 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5888. Min Range: -6.5888
Max Act: 6.3701. Min Act: -0.1700
Data Index: 5822179 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5888. Min Range: -6.5888
Max Act: 6.3701. Min Act: -0.1700
Data Index: 7789063 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5888. Min Range: -6.5888
Max Act: 6.3701. Min Act: -0.1700
Data Index: 7789085 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5888. Min Range: -6.5888
Max Act: 6.3388. Min Act: -0.1700
Data Index: 7789072 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5888. Min Range: -6.5888
Max Act: 6.3388. Min Act: -0.1700
Data Index: 5822178 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5888. Min Range: -6.5888
Max Act: 6.3388. Min Act: -0.1700
Data Index: 7789064 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19