Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2505 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6236. Min Range: -1.6236
Max Act: 1.6236. Min Act: -0.1700
Data Index: 8214654 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6236. Min Range: -1.6236
Max Act: 1.6062. Min Act: -0.1700
Data Index: 4508436 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6236. Min Range: -1.6236
Max Act: 1.5974. Min Act: -0.1700
Data Index: 8310798 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6236. Min Range: -1.6236
Max Act: 1.5799. Min Act: -0.1700
Data Index: 6302606 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6236. Min Range: -1.6236
Max Act: 1.5799. Min Act: -0.1699
Data Index: 7480260 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6236. Min Range: -1.6236
Max Act: 1.5625. Min Act: -0.1700
Data Index: 5977576 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6236. Min Range: -1.6236
Max Act: 1.5625. Min Act: -0.1699
Data Index: 3128209 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6236. Min Range: -1.6236
Max Act: 1.5712. Min Act: -0.1700
Data Index: 6570470 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6236. Min Range: -1.6236
Max Act: 1.5537. Min Act: -0.1697
Data Index: 4392278 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6236. Min Range: -1.6236
Max Act: 1.5625. Min Act: -0.1700
Data Index: 5164563 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6236. Min Range: -1.6236
Max Act: 1.5449. Min Act: -0.1700
Data Index: 3025932 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6236. Min Range: -1.6236
Max Act: 1.5362. Min Act: -0.1693
Data Index: 2462451 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6236. Min Range: -1.6236
Max Act: 1.5449. Min Act: -0.1700
Data Index: 3119408 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6236. Min Range: -1.6236
Max Act: 1.5449. Min Act: -0.1700
Data Index: 4676130 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6236. Min Range: -1.6236
Max Act: 1.5362. Min Act: -0.1700
Data Index: 5410806 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6236. Min Range: -1.6236
Max Act: 1.5274. Min Act: -0.1700
Data Index: 5638238 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6236. Min Range: -1.6236
Max Act: 1.5274. Min Act: -0.1700
Data Index: 3930130 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6236. Min Range: -1.6236
Max Act: 1.5274. Min Act: -0.1700
Data Index: 5288841 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6236. Min Range: -1.6236
Max Act: 1.5186. Min Act: -0.1700
Data Index: 6650247 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6236. Min Range: -1.6236
Max Act: 1.5099. Min Act: -0.1700
Data Index: 5178364 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19