Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1086 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6500. Min Range: -4.6500
Max Act: 4.6500. Min Act: -0.1700
Data Index: 2250418 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6500. Min Range: -4.6500
Max Act: 4.5563. Min Act: -0.1700
Data Index: 2803595 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6500. Min Range: -4.6500
Max Act: 4.5250. Min Act: -0.1700
Data Index: 7202191 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6500. Min Range: -4.6500
Max Act: 4.5875. Min Act: -0.1700
Data Index: 6119792 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6500. Min Range: -4.6500
Max Act: 4.6188. Min Act: -0.1700
Data Index: 8240709 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6500. Min Range: -4.6500
Max Act: 4.5875. Min Act: -0.1700
Data Index: 5701453 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6500. Min Range: -4.6500
Max Act: 4.5563. Min Act: -0.1700
Data Index: 261381 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6500. Min Range: -4.6500
Max Act: 4.4938. Min Act: -0.1700
Data Index: 1380789 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6500. Min Range: -4.6500
Max Act: 4.4625. Min Act: -0.1700
Data Index: 4065462 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6500. Min Range: -4.6500
Max Act: 4.4625. Min Act: -0.1700
Data Index: 953162 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6500. Min Range: -4.6500
Max Act: 4.4938. Min Act: -0.1700
Data Index: 7454741 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6500. Min Range: -4.6500
Max Act: 4.4625. Min Act: -0.1700
Data Index: 8716177 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6500. Min Range: -4.6500
Max Act: 4.4625. Min Act: -0.1700
Data Index: 5348365 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6500. Min Range: -4.6500
Max Act: 4.4313. Min Act: -0.1700
Data Index: 5871762 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6500. Min Range: -4.6500
Max Act: 4.4625. Min Act: -0.1700
Data Index: 7097090 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6500. Min Range: -4.6500
Max Act: 4.4313. Min Act: -0.1700
Data Index: 765266 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6500. Min Range: -4.6500
Max Act: 4.4000. Min Act: -0.1700
Data Index: 1986506 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6500. Min Range: -4.6500
Max Act: 4.4000. Min Act: -0.1700
Data Index: 1289289 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6500. Min Range: -4.6500
Max Act: 4.3688. Min Act: -0.1700
Data Index: 261454 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6500. Min Range: -4.6500
Max Act: 4.3688. Min Act: -0.1700
Data Index: 3660580 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19