Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2388 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.0802. Min Range: -1.0802
Max Act: 1.0802. Min Act: -0.1700
Data Index: 1912237 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0802. Min Range: -1.0802
Max Act: 1.0627. Min Act: -0.1700
Data Index: 5272379 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0802. Min Range: -1.0802
Max Act: 1.0540. Min Act: -0.1700
Data Index: 3544863 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0802. Min Range: -1.0802
Max Act: 1.0540. Min Act: -0.1700
Data Index: 6259178 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0802. Min Range: -1.0802
Max Act: 1.0453. Min Act: -0.1700
Data Index: 3106653 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0802. Min Range: -1.0802
Max Act: 1.0540. Min Act: -0.1700
Data Index: 7634936 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0802. Min Range: -1.0802
Max Act: 1.0453. Min Act: -0.1700
Data Index: 5751989 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0802. Min Range: -1.0802
Max Act: 1.0365. Min Act: -0.1700
Data Index: 4326095 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0802. Min Range: -1.0802
Max Act: 1.0365. Min Act: -0.1700
Data Index: 5688902 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0802. Min Range: -1.0802
Max Act: 1.0365. Min Act: -0.1700
Data Index: 7001709 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0802. Min Range: -1.0802
Max Act: 1.0191. Min Act: -0.1700
Data Index: 5578940 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0802. Min Range: -1.0802
Max Act: 1.0278. Min Act: -0.1700
Data Index: 5341772 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0802. Min Range: -1.0802
Max Act: 1.0104. Min Act: -0.1700
Data Index: 6483733 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0802. Min Range: -1.0802
Max Act: 1.0278. Min Act: -0.1700
Data Index: 8702641 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0802. Min Range: -1.0802
Max Act: 1.0278. Min Act: -0.1700
Data Index: 5694425 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0802. Min Range: -1.0802
Max Act: 1.0191. Min Act: -0.1700
Data Index: 3582045 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0802. Min Range: -1.0802
Max Act: 1.0104. Min Act: -0.1700
Data Index: 3986689 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0802. Min Range: -1.0802
Max Act: 1.0018. Min Act: -0.1700
Data Index: 7782134 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0802. Min Range: -1.0802
Max Act: 1.0104. Min Act: -0.1700
Data Index: 6945557 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0802. Min Range: -1.0802
Max Act: 1.0018. Min Act: -0.1700
Data Index: 7764142 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19