Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4176 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6023. Min Range: -4.6023
Max Act: 4.6023. Min Act: -0.1700
Data Index: 892341 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6023. Min Range: -4.6023
Max Act: 4.5711. Min Act: -0.1700
Data Index: 1791865 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6023. Min Range: -4.6023
Max Act: 4.5086. Min Act: -0.1700
Data Index: 1873716 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6023. Min Range: -4.6023
Max Act: 4.4773. Min Act: -0.1700
Data Index: 2356386 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6023. Min Range: -4.6023
Max Act: 4.4148. Min Act: -0.1700
Data Index: 4057319 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6023. Min Range: -4.6023
Max Act: 4.4148. Min Act: -0.1700
Data Index: 6947079 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6023. Min Range: -4.6023
Max Act: 4.3836. Min Act: -0.1700
Data Index: 5381020 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6023. Min Range: -4.6023
Max Act: 4.3523. Min Act: -0.1700
Data Index: 8109242 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6023. Min Range: -4.6023
Max Act: 4.3523. Min Act: -0.1700
Data Index: 98149 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6023. Min Range: -4.6023
Max Act: 4.3211. Min Act: -0.1700
Data Index: 964888 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6023. Min Range: -4.6023
Max Act: 4.3211. Min Act: -0.1700
Data Index: 7093948 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6023. Min Range: -4.6023
Max Act: 4.3211. Min Act: -0.1700
Data Index: 4410628 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6023. Min Range: -4.6023
Max Act: 4.3211. Min Act: -0.1700
Data Index: 1793443 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6023. Min Range: -4.6023
Max Act: 4.3211. Min Act: -0.1700
Data Index: 5755355 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6023. Min Range: -4.6023
Max Act: 4.2586. Min Act: -0.1700
Data Index: 5048738 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6023. Min Range: -4.6023
Max Act: 4.2898. Min Act: -0.1700
Data Index: 8592780 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6023. Min Range: -4.6023
Max Act: 4.2898. Min Act: -0.1700
Data Index: 8489415 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6023. Min Range: -4.6023
Max Act: 4.2898. Min Act: -0.1700
Data Index: 6849224 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6023. Min Range: -4.6023
Max Act: 4.2586. Min Act: -0.1700
Data Index: 2866450 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6023. Min Range: -4.6023
Max Act: 4.2898. Min Act: -0.1700
Data Index: 7002909 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19