Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3579 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8877. Min Range: -5.8877
Max Act: 5.8877. Min Act: -0.1700
Data Index: 4454025 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8877. Min Range: -5.8877
Max Act: 5.7627. Min Act: -0.1700
Data Index: 5440036 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8877. Min Range: -5.8877
Max Act: 5.6690. Min Act: -0.1700
Data Index: 6442031 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8877. Min Range: -5.8877
Max Act: 5.5752. Min Act: -0.1700
Data Index: 647123 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8877. Min Range: -5.8877
Max Act: 5.5440. Min Act: -0.1700
Data Index: 1811501 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8877. Min Range: -5.8877
Max Act: 5.5752. Min Act: -0.1700
Data Index: 3845204 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8877. Min Range: -5.8877
Max Act: 5.5127. Min Act: -0.1700
Data Index: 3505135 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8877. Min Range: -5.8877
Max Act: 5.5127. Min Act: -0.1700
Data Index: 7520419 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8877. Min Range: -5.8877
Max Act: 5.4502. Min Act: -0.1700
Data Index: 7926306 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8877. Min Range: -5.8877
Max Act: 5.4190. Min Act: -0.1700
Data Index: 3560962 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8877. Min Range: -5.8877
Max Act: 5.4502. Min Act: -0.1700
Data Index: 1554173 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8877. Min Range: -5.8877
Max Act: 5.3877. Min Act: -0.1700
Data Index: 5841559 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8877. Min Range: -5.8877
Max Act: 5.4190. Min Act: -0.1700
Data Index: 1146529 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8877. Min Range: -5.8877
Max Act: 5.3565. Min Act: -0.1700
Data Index: 8573816 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8877. Min Range: -5.8877
Max Act: 5.3877. Min Act: -0.1700
Data Index: 233119 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8877. Min Range: -5.8877
Max Act: 5.3252. Min Act: -0.1700
Data Index: 696794 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8877. Min Range: -5.8877
Max Act: 5.2627. Min Act: -0.1700
Data Index: 6478146 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8877. Min Range: -5.8877
Max Act: 5.2940. Min Act: -0.1700
Data Index: 6958946 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8877. Min Range: -5.8877
Max Act: 5.2940. Min Act: -0.1700
Data Index: 6285395 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8877. Min Range: -5.8877
Max Act: 5.2627. Min Act: -0.1700
Data Index: 6561868 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19