Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2883 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.4690. Min Act: -0.1700
Data Index: 5024450 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.3440. Min Act: -0.1700
Data Index: 1944492 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.3752. Min Act: -0.1700
Data Index: 4970974 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.3127. Min Act: -0.1700
Data Index: 5139998 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.2815. Min Act: -0.1700
Data Index: 8065276 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.2502. Min Act: -0.1700
Data Index: 3905560 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.2190. Min Act: -0.1700
Data Index: 4857388 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.1877. Min Act: -0.1700
Data Index: 3490408 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.1877. Min Act: -0.1700
Data Index: 4999320 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.1877. Min Act: -0.1700
Data Index: 5844187 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.1877. Min Act: -0.1700
Data Index: 6857864 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.1877. Min Act: -0.1700
Data Index: 7151661 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.1252. Min Act: -0.1700
Data Index: 3051623 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.1252. Min Act: -0.1700
Data Index: 3051621 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.0940. Min Act: -0.1700
Data Index: 1412665 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.1252. Min Act: -0.1700
Data Index: 3736121 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.1565. Min Act: -0.1700
Data Index: 3309369 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.1565. Min Act: -0.1700
Data Index: 4310529 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.0627. Min Act: -0.1700
Data Index: 3829089 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.0940. Min Act: -0.1700
Data Index: 1109010 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19