Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2103 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.8673. Min Act: -0.1700
Data Index: 965987 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.8673. Min Act: -0.1700
Data Index: 6267489 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.7735. Min Act: -0.1700
Data Index: 1810963 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.7423. Min Act: -0.1700
Data Index: 7311658 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.6798. Min Act: -0.1700
Data Index: 3915839 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.7110. Min Act: -0.1700
Data Index: 4021784 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.7110. Min Act: -0.1700
Data Index: 3449663 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.7110. Min Act: -0.1700
Data Index: 6766033 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.6798. Min Act: -0.1700
Data Index: 3784419 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.6798. Min Act: -0.1700
Data Index: 120406 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.6798. Min Act: -0.1700
Data Index: 3276815 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.6485. Min Act: -0.1700
Data Index: 4095712 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.6485. Min Act: -0.1700
Data Index: 8291209 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.6485. Min Act: -0.1700
Data Index: 1193208 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.6173. Min Act: -0.1700
Data Index: 7333660 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.6173. Min Act: -0.1700
Data Index: 1443739 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.5860. Min Act: -0.1700
Data Index: 1855835 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.5860. Min Act: -0.1700
Data Index: 4640096 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.5860. Min Act: -0.1700
Data Index: 5127863 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8673. Min Range: -4.8673
Max Act: 4.5860. Min Act: -0.1700
Data Index: 2498654 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19