Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2290 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8282. Min Range: -2.8282
Max Act: 2.8282. Min Act: -0.1700
Data Index: 1837523 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8282. Min Range: -2.8282
Max Act: 2.7804. Min Act: -0.1700
Data Index: 4213112 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8282. Min Range: -2.8282
Max Act: 2.7804. Min Act: -0.1700
Data Index: 2470590 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8282. Min Range: -2.8282
Max Act: 2.7645. Min Act: -0.1700
Data Index: 1355358 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8282. Min Range: -2.8282
Max Act: 2.7006. Min Act: -0.1700
Data Index: 776341 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8282. Min Range: -2.8282
Max Act: 2.7166. Min Act: -0.1700
Data Index: 3176822 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8282. Min Range: -2.8282
Max Act: 2.7006. Min Act: -0.1700
Data Index: 1147049 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8282. Min Range: -2.8282
Max Act: 2.6846. Min Act: -0.1700
Data Index: 1702726 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8282. Min Range: -2.8282
Max Act: 2.6846. Min Act: -0.1700
Data Index: 1662367 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8282. Min Range: -2.8282
Max Act: 2.6685. Min Act: -0.1700
Data Index: 2108000 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8282. Min Range: -2.8282
Max Act: 2.6685. Min Act: -0.1700
Data Index: 2452255 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8282. Min Range: -2.8282
Max Act: 2.6846. Min Act: -0.1700
Data Index: 7178039 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8282. Min Range: -2.8282
Max Act: 2.6846. Min Act: -0.1700
Data Index: 1206218 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8282. Min Range: -2.8282
Max Act: 2.6525. Min Act: -0.1700
Data Index: 6613594 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8282. Min Range: -2.8282
Max Act: 2.6525. Min Act: -0.1700
Data Index: 4309577 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8282. Min Range: -2.8282
Max Act: 2.6204. Min Act: -0.1700
Data Index: 4331803 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8282. Min Range: -2.8282
Max Act: 2.6525. Min Act: -0.1700
Data Index: 4847910 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8282. Min Range: -2.8282
Max Act: 2.6365. Min Act: -0.1700
Data Index: 1577129 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8282. Min Range: -2.8282
Max Act: 2.6525. Min Act: -0.1700
Data Index: 901335 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8282. Min Range: -2.8282
Max Act: 2.6525. Min Act: -0.1700
Data Index: 780860 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19