Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 656 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0481. Min Range: -6.0481
Max Act: 6.0481. Min Act: -0.1700
Data Index: 4587490 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0481. Min Range: -6.0481
Max Act: 6.0481. Min Act: -0.1700
Data Index: 8094436 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0481. Min Range: -6.0481
Max Act: 6.0169. Min Act: -0.1700
Data Index: 5716055 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0481. Min Range: -6.0481
Max Act: 5.9544. Min Act: -0.1700
Data Index: 318119 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0481. Min Range: -6.0481
Max Act: 5.9544. Min Act: -0.1700
Data Index: 2492643 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0481. Min Range: -6.0481
Max Act: 5.9544. Min Act: -0.1700
Data Index: 7328255 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0481. Min Range: -6.0481
Max Act: 5.9856. Min Act: -0.1700
Data Index: 3326250 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0481. Min Range: -6.0481
Max Act: 5.9544. Min Act: -0.1700
Data Index: 2978495 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0481. Min Range: -6.0481
Max Act: 5.9544. Min Act: -0.1700
Data Index: 6273858 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0481. Min Range: -6.0481
Max Act: 5.9544. Min Act: -0.1700
Data Index: 2296774 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0481. Min Range: -6.0481
Max Act: 5.8919. Min Act: -0.1700
Data Index: 7189796 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0481. Min Range: -6.0481
Max Act: 5.8919. Min Act: -0.1700
Data Index: 564902 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0481. Min Range: -6.0481
Max Act: 5.9231. Min Act: -0.1700
Data Index: 2503211 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0481. Min Range: -6.0481
Max Act: 5.9231. Min Act: -0.1700
Data Index: 2115471 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0481. Min Range: -6.0481
Max Act: 5.8919. Min Act: -0.1700
Data Index: 8018071 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0481. Min Range: -6.0481
Max Act: 5.8919. Min Act: -0.1700
Data Index: 255686 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0481. Min Range: -6.0481
Max Act: 5.8919. Min Act: -0.1700
Data Index: 2650822 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0481. Min Range: -6.0481
Max Act: 5.8919. Min Act: -0.1700
Data Index: 181210 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0481. Min Range: -6.0481
Max Act: 5.8606. Min Act: -0.1700
Data Index: 2036516 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0481. Min Range: -6.0481
Max Act: 5.8919. Min Act: -0.1700
Data Index: 4370741 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19