Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4491 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1524. Min Range: -5.1524
Max Act: 5.1524. Min Act: -0.1700
Data Index: 5731373 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.9961. Min Act: -0.1700
Data Index: 7732318 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.9961. Min Act: -0.1700
Data Index: 6857074 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.9961. Min Act: -0.1700
Data Index: 1946891 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.9649. Min Act: -0.1700
Data Index: 6377795 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.8711. Min Act: -0.1700
Data Index: 2002272 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.8711. Min Act: -0.1700
Data Index: 5227226 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.8711. Min Act: -0.1700
Data Index: 388019 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.8399. Min Act: -0.1700
Data Index: 1629629 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.8399. Min Act: -0.1700
Data Index: 503279 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.8086. Min Act: -0.1700
Data Index: 617575 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.8086. Min Act: -0.1700
Data Index: 2579293 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.7774. Min Act: -0.1700
Data Index: 5858979 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.7774. Min Act: -0.1700
Data Index: 754909 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.7774. Min Act: -0.1700
Data Index: 1264160 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.7774. Min Act: -0.1700
Data Index: 1833020 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.7461. Min Act: -0.1700
Data Index: 1170157 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.7149. Min Act: -0.1700
Data Index: 3925781 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.7149. Min Act: -0.1700
Data Index: 1254867 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1524. Min Range: -5.1524
Max Act: 4.6836. Min Act: -0.1700
Data Index: 5970253 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19