Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 483 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4769. Min Range: -5.4769
Max Act: 5.4769. Min Act: -0.1700
Data Index: 1974349 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4769. Min Range: -5.4769
Max Act: 5.4144. Min Act: -0.1700
Data Index: 8530516 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4769. Min Range: -5.4769
Max Act: 5.3207. Min Act: -0.1700
Data Index: 3921708 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4769. Min Range: -5.4769
Max Act: 5.3207. Min Act: -0.1700
Data Index: 6002830 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4769. Min Range: -5.4769
Max Act: 5.2894. Min Act: -0.1700
Data Index: 1685135 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4769. Min Range: -5.4769
Max Act: 5.2582. Min Act: -0.1700
Data Index: 8402334 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4769. Min Range: -5.4769
Max Act: 5.2894. Min Act: -0.1700
Data Index: 4202795 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4769. Min Range: -5.4769
Max Act: 5.2269. Min Act: -0.1700
Data Index: 3635496 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4769. Min Range: -5.4769
Max Act: 5.1957. Min Act: -0.1700
Data Index: 1451549 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4769. Min Range: -5.4769
Max Act: 5.1644. Min Act: -0.1700
Data Index: 1712294 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4769. Min Range: -5.4769
Max Act: 5.1957. Min Act: -0.1700
Data Index: 5706987 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4769. Min Range: -5.4769
Max Act: 5.1957. Min Act: -0.1700
Data Index: 7316245 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4769. Min Range: -5.4769
Max Act: 5.1332. Min Act: -0.1700
Data Index: 6823910 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4769. Min Range: -5.4769
Max Act: 5.1332. Min Act: -0.1700
Data Index: 8514272 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4769. Min Range: -5.4769
Max Act: 5.1644. Min Act: -0.1700
Data Index: 2993921 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4769. Min Range: -5.4769
Max Act: 5.1019. Min Act: -0.1700
Data Index: 8577507 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4769. Min Range: -5.4769
Max Act: 5.1019. Min Act: -0.1700
Data Index: 3926836 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4769. Min Range: -5.4769
Max Act: 5.1019. Min Act: -0.1700
Data Index: 4072719 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4769. Min Range: -5.4769
Max Act: 5.1019. Min Act: -0.1700
Data Index: 8353702 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4769. Min Range: -5.4769
Max Act: 5.1019. Min Act: -0.1700
Data Index: 4037407 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19