Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2558 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6860. Min Range: -8.6860
Max Act: 8.6860. Min Act: -0.1700
Data Index: 5534995 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6860. Min Range: -8.6860
Max Act: 8.3110. Min Act: -0.1700
Data Index: 4762872 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6860. Min Range: -8.6860
Max Act: 8.2485. Min Act: -0.1700
Data Index: 315681 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6860. Min Range: -8.6860
Max Act: 8.1235. Min Act: -0.1700
Data Index: 6926734 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6860. Min Range: -8.6860
Max Act: 8.1860. Min Act: -0.1700
Data Index: 7818230 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6860. Min Range: -8.6860
Max Act: 8.1235. Min Act: -0.1700
Data Index: 283464 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6860. Min Range: -8.6860
Max Act: 8.1860. Min Act: -0.1700
Data Index: 1393760 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6860. Min Range: -8.6860
Max Act: 8.1235. Min Act: -0.1700
Data Index: 7587319 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6860. Min Range: -8.6860
Max Act: 8.0610. Min Act: -0.1700
Data Index: 4223794 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6860. Min Range: -8.6860
Max Act: 8.0610. Min Act: -0.1700
Data Index: 7635970 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6860. Min Range: -8.6860
Max Act: 7.9985. Min Act: -0.1700
Data Index: 3714757 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6860. Min Range: -8.6860
Max Act: 8.0610. Min Act: -0.1700
Data Index: 2028615 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6860. Min Range: -8.6860
Max Act: 7.9360. Min Act: -0.1700
Data Index: 2417530 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6860. Min Range: -8.6860
Max Act: 7.9360. Min Act: -0.1700
Data Index: 6379716 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6860. Min Range: -8.6860
Max Act: 7.9360. Min Act: -0.1700
Data Index: 2417531 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6860. Min Range: -8.6860
Max Act: 7.9360. Min Act: -0.1700
Data Index: 3947624 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6860. Min Range: -8.6860
Max Act: 7.8735. Min Act: -0.1700
Data Index: 2306143 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6860. Min Range: -8.6860
Max Act: 7.8735. Min Act: -0.1700
Data Index: 2306144 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6860. Min Range: -8.6860
Max Act: 7.8735. Min Act: -0.1700
Data Index: 4807403 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6860. Min Range: -8.6860
Max Act: 7.8110. Min Act: -0.1700
Data Index: 7513240 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19