Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1394 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.1467. Min Range: -9.1467
Max Act: 9.1467. Min Act: -0.1700
Data Index: 4045784 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1467. Min Range: -9.1467
Max Act: 8.8967. Min Act: -0.1700
Data Index: 4960308 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1467. Min Range: -9.1467
Max Act: 8.5842. Min Act: -0.1700
Data Index: 6158093 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1467. Min Range: -9.1467
Max Act: 8.5842. Min Act: -0.1700
Data Index: 3341797 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1467. Min Range: -9.1467
Max Act: 8.5842. Min Act: -0.1700
Data Index: 6476401 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1467. Min Range: -9.1467
Max Act: 8.5217. Min Act: -0.1700
Data Index: 6151723 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1467. Min Range: -9.1467
Max Act: 8.5217. Min Act: -0.1700
Data Index: 5196163 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1467. Min Range: -9.1467
Max Act: 8.5217. Min Act: -0.1700
Data Index: 1881523 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1467. Min Range: -9.1467
Max Act: 8.4592. Min Act: -0.1700
Data Index: 4541871 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1467. Min Range: -9.1467
Max Act: 8.4592. Min Act: -0.1700
Data Index: 6873592 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1467. Min Range: -9.1467
Max Act: 8.4592. Min Act: -0.1700
Data Index: 1406757 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1467. Min Range: -9.1467
Max Act: 8.3342. Min Act: -0.1700
Data Index: 1449827 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1467. Min Range: -9.1467
Max Act: 8.3967. Min Act: -0.1700
Data Index: 4960306 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1467. Min Range: -9.1467
Max Act: 8.3342. Min Act: -0.1700
Data Index: 3672364 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1467. Min Range: -9.1467
Max Act: 8.3342. Min Act: -0.1700
Data Index: 2300808 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1467. Min Range: -9.1467
Max Act: 8.3342. Min Act: -0.1700
Data Index: 381110 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1467. Min Range: -9.1467
Max Act: 8.2717. Min Act: -0.1700
Data Index: 3805007 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1467. Min Range: -9.1467
Max Act: 8.2717. Min Act: -0.1700
Data Index: 2008123 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1467. Min Range: -9.1467
Max Act: 8.2717. Min Act: -0.1700
Data Index: 439150 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1467. Min Range: -9.1467
Max Act: 8.2717. Min Act: -0.1700
Data Index: 4116615 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19