Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 979 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8308. Min Range: -5.8308
Max Act: 5.8308. Min Act: -0.1700
Data Index: 6688675 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8308. Min Range: -5.8308
Max Act: 5.5808. Min Act: -0.1700
Data Index: 7086845 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8308. Min Range: -5.8308
Max Act: 5.5808. Min Act: -0.1700
Data Index: 4277664 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8308. Min Range: -5.8308
Max Act: 5.5496. Min Act: -0.1700
Data Index: 312298 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8308. Min Range: -5.8308
Max Act: 5.5183. Min Act: -0.1700
Data Index: 5945904 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8308. Min Range: -5.8308
Max Act: 5.4558. Min Act: -0.1700
Data Index: 6025301 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8308. Min Range: -5.8308
Max Act: 5.4246. Min Act: -0.1700
Data Index: 3782336 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8308. Min Range: -5.8308
Max Act: 5.3933. Min Act: -0.1700
Data Index: 7865596 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8308. Min Range: -5.8308
Max Act: 5.3933. Min Act: -0.1700
Data Index: 6468077 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8308. Min Range: -5.8308
Max Act: 5.3621. Min Act: -0.1700
Data Index: 1458756 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8308. Min Range: -5.8308
Max Act: 5.3308. Min Act: -0.1700
Data Index: 7672989 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8308. Min Range: -5.8308
Max Act: 5.2371. Min Act: -0.1700
Data Index: 3751002 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8308. Min Range: -5.8308
Max Act: 5.2371. Min Act: -0.1700
Data Index: 4823291 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8308. Min Range: -5.8308
Max Act: 5.2371. Min Act: -0.1700
Data Index: 7352756 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8308. Min Range: -5.8308
Max Act: 5.2058. Min Act: -0.1700
Data Index: 4282768 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8308. Min Range: -5.8308
Max Act: 5.2058. Min Act: -0.1700
Data Index: 3870435 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8308. Min Range: -5.8308
Max Act: 5.1746. Min Act: -0.1700
Data Index: 3607139 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8308. Min Range: -5.8308
Max Act: 5.1433. Min Act: -0.1700
Data Index: 8793416 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8308. Min Range: -5.8308
Max Act: 5.1433. Min Act: -0.1700
Data Index: 2027504 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8308. Min Range: -5.8308
Max Act: 5.1121. Min Act: -0.1700
Data Index: 5866380 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19