Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1345 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5079. Min Range: -6.5079
Max Act: 6.5079. Min Act: -0.1700
Data Index: 3392492 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5079. Min Range: -6.5079
Max Act: 6.3517. Min Act: -0.1700
Data Index: 1028758 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5079. Min Range: -6.5079
Max Act: 6.2579. Min Act: -0.1700
Data Index: 6113198 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5079. Min Range: -6.5079
Max Act: 6.2267. Min Act: -0.1700
Data Index: 218397 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5079. Min Range: -6.5079
Max Act: 6.1954. Min Act: -0.1700
Data Index: 4696491 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5079. Min Range: -6.5079
Max Act: 6.1329. Min Act: -0.1700
Data Index: 5120155 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5079. Min Range: -6.5079
Max Act: 6.1017. Min Act: -0.1700
Data Index: 8287182 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5079. Min Range: -6.5079
Max Act: 6.1017. Min Act: -0.1700
Data Index: 5362885 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5079. Min Range: -6.5079
Max Act: 6.0704. Min Act: -0.1700
Data Index: 8336527 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5079. Min Range: -6.5079
Max Act: 6.0392. Min Act: -0.1700
Data Index: 304244 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5079. Min Range: -6.5079
Max Act: 6.1017. Min Act: -0.1700
Data Index: 6051064 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5079. Min Range: -6.5079
Max Act: 6.0704. Min Act: -0.1700
Data Index: 6012924 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5079. Min Range: -6.5079
Max Act: 6.0704. Min Act: -0.1700
Data Index: 5713283 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5079. Min Range: -6.5079
Max Act: 6.0079. Min Act: -0.1700
Data Index: 3242702 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5079. Min Range: -6.5079
Max Act: 6.0392. Min Act: -0.1700
Data Index: 7320707 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5079. Min Range: -6.5079
Max Act: 6.0079. Min Act: -0.1700
Data Index: 300999 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5079. Min Range: -6.5079
Max Act: 6.0392. Min Act: -0.1700
Data Index: 6483386 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5079. Min Range: -6.5079
Max Act: 5.9767. Min Act: -0.1700
Data Index: 557413 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5079. Min Range: -6.5079
Max Act: 5.9454. Min Act: -0.1700
Data Index: 1958622 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5079. Min Range: -6.5079
Max Act: 6.0079. Min Act: -0.1700
Data Index: 3242701 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19