Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3816 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5805. Min Range: -5.5805
Max Act: 5.5805. Min Act: -0.1700
Data Index: 5233236 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5805. Min Range: -5.5805
Max Act: 5.4243. Min Act: -0.1700
Data Index: 8322603 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5805. Min Range: -5.5805
Max Act: 5.4868. Min Act: -0.1700
Data Index: 3482743 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5805. Min Range: -5.5805
Max Act: 5.4555. Min Act: -0.1700
Data Index: 4593376 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5805. Min Range: -5.5805
Max Act: 5.4243. Min Act: -0.1700
Data Index: 7891964 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5805. Min Range: -5.5805
Max Act: 5.4243. Min Act: -0.1700
Data Index: 5124383 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5805. Min Range: -5.5805
Max Act: 5.3618. Min Act: -0.1700
Data Index: 8040828 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5805. Min Range: -5.5805
Max Act: 5.3305. Min Act: -0.1700
Data Index: 2520963 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5805. Min Range: -5.5805
Max Act: 5.3618. Min Act: -0.1700
Data Index: 2807932 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5805. Min Range: -5.5805
Max Act: 5.2993. Min Act: -0.1700
Data Index: 5923652 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5805. Min Range: -5.5805
Max Act: 5.2680. Min Act: -0.1698
Data Index: 2430325 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5805. Min Range: -5.5805
Max Act: 5.2368. Min Act: -0.1700
Data Index: 2004031 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5805. Min Range: -5.5805
Max Act: 5.2680. Min Act: -0.1697
Data Index: 7299490 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5805. Min Range: -5.5805
Max Act: 5.2368. Min Act: -0.1697
Data Index: 4388622 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5805. Min Range: -5.5805
Max Act: 5.2368. Min Act: -0.1700
Data Index: 6829527 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5805. Min Range: -5.5805
Max Act: 5.2368. Min Act: -0.1700
Data Index: 8757387 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5805. Min Range: -5.5805
Max Act: 5.1743. Min Act: -0.1700
Data Index: 2540887 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5805. Min Range: -5.5805
Max Act: 5.2055. Min Act: -0.1700
Data Index: 2553799 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5805. Min Range: -5.5805
Max Act: 5.1743. Min Act: -0.1700
Data Index: 2323163 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5805. Min Range: -5.5805
Max Act: 5.2055. Min Act: -0.1699
Data Index: 8686920 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19