Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3238 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3638. Min Range: -5.3638
Max Act: 5.3638. Min Act: -0.1700
Data Index: 1546448 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3638. Min Range: -5.3638
Max Act: 5.2388. Min Act: -0.1700
Data Index: 8361446 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3638. Min Range: -5.3638
Max Act: 5.2075. Min Act: -0.1700
Data Index: 8601809 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3638. Min Range: -5.3638
Max Act: 5.2075. Min Act: -0.1700
Data Index: 4360373 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3638. Min Range: -5.3638
Max Act: 5.1763. Min Act: -0.1700
Data Index: 495471 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3638. Min Range: -5.3638
Max Act: 5.1450. Min Act: -0.1700
Data Index: 3557639 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3638. Min Range: -5.3638
Max Act: 5.1450. Min Act: -0.1700
Data Index: 6344759 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3638. Min Range: -5.3638
Max Act: 5.1138. Min Act: -0.1700
Data Index: 7532 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3638. Min Range: -5.3638
Max Act: 5.1138. Min Act: -0.1700
Data Index: 7862782 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3638. Min Range: -5.3638
Max Act: 5.1138. Min Act: -0.1700
Data Index: 6035067 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3638. Min Range: -5.3638
Max Act: 5.1138. Min Act: -0.1700
Data Index: 2380530 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3638. Min Range: -5.3638
Max Act: 5.1138. Min Act: -0.1700
Data Index: 7337953 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3638. Min Range: -5.3638
Max Act: 5.0825. Min Act: -0.1700
Data Index: 988444 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3638. Min Range: -5.3638
Max Act: 5.0825. Min Act: -0.1700
Data Index: 4363277 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3638. Min Range: -5.3638
Max Act: 5.0825. Min Act: -0.1700
Data Index: 7051125 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3638. Min Range: -5.3638
Max Act: 5.0825. Min Act: -0.1700
Data Index: 1190569 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3638. Min Range: -5.3638
Max Act: 5.0825. Min Act: -0.1700
Data Index: 6604668 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3638. Min Range: -5.3638
Max Act: 5.0825. Min Act: -0.1700
Data Index: 3562955 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3638. Min Range: -5.3638
Max Act: 5.0825. Min Act: -0.1700
Data Index: 4778848 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3638. Min Range: -5.3638
Max Act: 5.0825. Min Act: -0.1700
Data Index: 4525530 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19