Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3482 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1822. Min Range: -5.1822
Max Act: 5.1822. Min Act: -0.1700
Data Index: 5030760 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1822. Min Range: -5.1822
Max Act: 5.0885. Min Act: -0.1700
Data Index: 4352099 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1822. Min Range: -5.1822
Max Act: 5.0260. Min Act: -0.1700
Data Index: 6070493 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1822. Min Range: -5.1822
Max Act: 4.9635. Min Act: -0.1700
Data Index: 8116864 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1822. Min Range: -5.1822
Max Act: 4.9322. Min Act: -0.1700
Data Index: 6598320 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1822. Min Range: -5.1822
Max Act: 4.9322. Min Act: -0.1700
Data Index: 4091926 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1822. Min Range: -5.1822
Max Act: 4.9010. Min Act: -0.1700
Data Index: 6028299 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1822. Min Range: -5.1822
Max Act: 4.8697. Min Act: -0.1700
Data Index: 8564488 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1822. Min Range: -5.1822
Max Act: 4.9010. Min Act: -0.1700
Data Index: 1186465 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1822. Min Range: -5.1822
Max Act: 4.8697. Min Act: -0.1700
Data Index: 7587895 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1822. Min Range: -5.1822
Max Act: 4.8697. Min Act: -0.1700
Data Index: 4685254 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1822. Min Range: -5.1822
Max Act: 4.8697. Min Act: -0.1700
Data Index: 7024215 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1822. Min Range: -5.1822
Max Act: 4.8697. Min Act: -0.1700
Data Index: 5653496 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1822. Min Range: -5.1822
Max Act: 4.8385. Min Act: -0.1700
Data Index: 8303542 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1822. Min Range: -5.1822
Max Act: 4.8697. Min Act: -0.1700
Data Index: 3032833 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1822. Min Range: -5.1822
Max Act: 4.8385. Min Act: -0.1700
Data Index: 914277 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1822. Min Range: -5.1822
Max Act: 4.8385. Min Act: -0.1700
Data Index: 6779005 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1822. Min Range: -5.1822
Max Act: 4.8385. Min Act: -0.1700
Data Index: 6710617 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1822. Min Range: -5.1822
Max Act: 4.8385. Min Act: -0.1700
Data Index: 1713506 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1822. Min Range: -5.1822
Max Act: 4.8385. Min Act: -0.1700
Data Index: 411660 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19