Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 908 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.3533. Min Range: -10.3533
Max Act: 10.3533. Min Act: -0.1700
Data Index: 8052894 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3533. Min Range: -10.3533
Max Act: 10.2283. Min Act: -0.1700
Data Index: 8223140 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3533. Min Range: -10.3533
Max Act: 10.2283. Min Act: -0.1700
Data Index: 720505 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3533. Min Range: -10.3533
Max Act: 10.1658. Min Act: -0.1700
Data Index: 980419 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3533. Min Range: -10.3533
Max Act: 10.1033. Min Act: -0.1700
Data Index: 5848798 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3533. Min Range: -10.3533
Max Act: 10.0408. Min Act: -0.1700
Data Index: 1584926 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3533. Min Range: -10.3533
Max Act: 10.1658. Min Act: -0.1700
Data Index: 2183143 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3533. Min Range: -10.3533
Max Act: 10.0408. Min Act: -0.1700
Data Index: 6773793 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3533. Min Range: -10.3533
Max Act: 10.1033. Min Act: -0.1700
Data Index: 717025 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3533. Min Range: -10.3533
Max Act: 10.0408. Min Act: -0.1700
Data Index: 4435382 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3533. Min Range: -10.3533
Max Act: 10.1033. Min Act: -0.1700
Data Index: 5839197 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3533. Min Range: -10.3533
Max Act: 10.0408. Min Act: -0.1700
Data Index: 1520994 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3533. Min Range: -10.3533
Max Act: 9.9783. Min Act: -0.1700
Data Index: 4765673 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3533. Min Range: -10.3533
Max Act: 9.9158. Min Act: -0.1700
Data Index: 7956448 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3533. Min Range: -10.3533
Max Act: 9.8533. Min Act: -0.1700
Data Index: 7900068 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3533. Min Range: -10.3533
Max Act: 9.8533. Min Act: -0.1700
Data Index: 2218830 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3533. Min Range: -10.3533
Max Act: 9.9158. Min Act: -0.1700
Data Index: 1337701 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3533. Min Range: -10.3533
Max Act: 9.9158. Min Act: -0.1700
Data Index: 5959932 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3533. Min Range: -10.3533
Max Act: 9.8533. Min Act: -0.1700
Data Index: 4094512 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3533. Min Range: -10.3533
Max Act: 9.8533. Min Act: -0.1700
Data Index: 686452 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19