Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1048 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1572. Min Range: -5.1572
Max Act: 5.1572. Min Act: -0.1700
Data Index: 8558587 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1572. Min Range: -5.1572
Max Act: 5.1260. Min Act: -0.1700
Data Index: 8372952 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1572. Min Range: -5.1572
Max Act: 5.0635. Min Act: -0.1700
Data Index: 3132980 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1572. Min Range: -5.1572
Max Act: 5.0322. Min Act: -0.1700
Data Index: 4163908 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1572. Min Range: -5.1572
Max Act: 5.0010. Min Act: -0.1700
Data Index: 3580239 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1572. Min Range: -5.1572
Max Act: 4.9385. Min Act: -0.1700
Data Index: 2661525 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1572. Min Range: -5.1572
Max Act: 4.9072. Min Act: -0.1700
Data Index: 4636939 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1572. Min Range: -5.1572
Max Act: 4.9385. Min Act: -0.1700
Data Index: 3851925 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1572. Min Range: -5.1572
Max Act: 4.9072. Min Act: -0.1700
Data Index: 8292078 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1572. Min Range: -5.1572
Max Act: 4.9072. Min Act: -0.1700
Data Index: 3420881 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1572. Min Range: -5.1572
Max Act: 4.8760. Min Act: -0.1700
Data Index: 3131245 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1572. Min Range: -5.1572
Max Act: 4.8760. Min Act: -0.1700
Data Index: 7792 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1572. Min Range: -5.1572
Max Act: 4.8447. Min Act: -0.1700
Data Index: 7819449 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1572. Min Range: -5.1572
Max Act: 4.8760. Min Act: -0.1700
Data Index: 1022253 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1572. Min Range: -5.1572
Max Act: 4.8447. Min Act: -0.1700
Data Index: 935217 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1572. Min Range: -5.1572
Max Act: 4.8135. Min Act: -0.1700
Data Index: 814473 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1572. Min Range: -5.1572
Max Act: 4.8135. Min Act: -0.1700
Data Index: 5881982 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1572. Min Range: -5.1572
Max Act: 4.8135. Min Act: -0.1700
Data Index: 604404 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1572. Min Range: -5.1572
Max Act: 4.8135. Min Act: -0.1700
Data Index: 5087372 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1572. Min Range: -5.1572
Max Act: 4.7822. Min Act: -0.1700
Data Index: 772226 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19