Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2165 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0465. Min Range: -4.0465
Max Act: 4.0152. Min Act: -0.1700
Data Index: 4784199 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0465. Min Range: -4.0465
Max Act: 4.0465. Min Act: -0.1700
Data Index: 7059418 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0465. Min Range: -4.0465
Max Act: 3.9527. Min Act: -0.1700
Data Index: 109470 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0465. Min Range: -4.0465
Max Act: 3.8589. Min Act: -0.1700
Data Index: 4563737 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0465. Min Range: -4.0465
Max Act: 3.9215. Min Act: -0.1700
Data Index: 4527242 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0465. Min Range: -4.0465
Max Act: 3.9840. Min Act: -0.1700
Data Index: 4291172 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0465. Min Range: -4.0465
Max Act: 3.7964. Min Act: -0.1700
Data Index: 115009 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0465. Min Range: -4.0465
Max Act: 3.9215. Min Act: -0.1700
Data Index: 7654776 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0465. Min Range: -4.0465
Max Act: 3.7338. Min Act: -0.1700
Data Index: 143109 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0465. Min Range: -4.0465
Max Act: 3.8589. Min Act: -0.1700
Data Index: 4850762 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0465. Min Range: -4.0465
Max Act: 3.8589. Min Act: -0.1700
Data Index: 422445 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0465. Min Range: -4.0465
Max Act: 3.9215. Min Act: -0.1700
Data Index: 3017249 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0465. Min Range: -4.0465
Max Act: 3.7964. Min Act: -0.1700
Data Index: 6934333 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0465. Min Range: -4.0465
Max Act: 3.8589. Min Act: -0.1700
Data Index: 3353843 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0465. Min Range: -4.0465
Max Act: 3.8589. Min Act: -0.1700
Data Index: 7582951 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0465. Min Range: -4.0465
Max Act: 3.8277. Min Act: -0.1700
Data Index: 5930187 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0465. Min Range: -4.0465
Max Act: 3.7338. Min Act: -0.1700
Data Index: 475449 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0465. Min Range: -4.0465
Max Act: 3.7025. Min Act: -0.1700
Data Index: 1753487 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0465. Min Range: -4.0465
Max Act: 3.7964. Min Act: -0.1700
Data Index: 3160868 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0465. Min Range: -4.0465
Max Act: 3.8277. Min Act: -0.1700
Data Index: 5348371 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19