Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3359 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9387. Min Range: -2.9387
Max Act: 2.9387. Min Act: -0.1700
Data Index: 5870387 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9387. Min Range: -2.9387
Max Act: 2.9070. Min Act: -0.1700
Data Index: 6810069 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9387. Min Range: -2.9387
Max Act: 2.8911. Min Act: -0.1700
Data Index: 4912205 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9387. Min Range: -2.9387
Max Act: 2.8752. Min Act: -0.1700
Data Index: 7920760 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9387. Min Range: -2.9387
Max Act: 2.8594. Min Act: -0.1700
Data Index: 3496368 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9387. Min Range: -2.9387
Max Act: 2.8435. Min Act: -0.1700
Data Index: 1749192 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9387. Min Range: -2.9387
Max Act: 2.8276. Min Act: -0.1700
Data Index: 3055731 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9387. Min Range: -2.9387
Max Act: 2.8276. Min Act: -0.1700
Data Index: 399103 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9387. Min Range: -2.9387
Max Act: 2.8276. Min Act: -0.1700
Data Index: 3115557 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9387. Min Range: -2.9387
Max Act: 2.8276. Min Act: -0.1700
Data Index: 5960079 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9387. Min Range: -2.9387
Max Act: 2.8276. Min Act: -0.1700
Data Index: 1455018 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9387. Min Range: -2.9387
Max Act: 2.8117. Min Act: -0.1700
Data Index: 6594610 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9387. Min Range: -2.9387
Max Act: 2.8117. Min Act: -0.1700
Data Index: 5216849 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9387. Min Range: -2.9387
Max Act: 2.8117. Min Act: -0.1700
Data Index: 8608889 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9387. Min Range: -2.9387
Max Act: 2.7957. Min Act: -0.1700
Data Index: 3619180 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9387. Min Range: -2.9387
Max Act: 2.7798. Min Act: -0.1700
Data Index: 5045041 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9387. Min Range: -2.9387
Max Act: 2.8117. Min Act: -0.1700
Data Index: 2237434 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9387. Min Range: -2.9387
Max Act: 2.8117. Min Act: -0.1700
Data Index: 1823878 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9387. Min Range: -2.9387
Max Act: 2.7798. Min Act: -0.1700
Data Index: 1000558 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9387. Min Range: -2.9387
Max Act: 2.7957. Min Act: -0.1700
Data Index: 4539787 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19