Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1099 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.2231. Min Range: -0.2231
Max Act: 0.2231. Min Act: -0.1700
Data Index: 8458931 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2231. Min Range: -0.2231
Max Act: 0.2231. Min Act: -0.1700
Data Index: 1743621 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2231. Min Range: -0.2231
Max Act: 0.2231. Min Act: -0.1700
Data Index: 3679607 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2231. Min Range: -0.2231
Max Act: 0.2231. Min Act: -0.1700
Data Index: 6395432 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2231. Min Range: -0.2231
Max Act: 0.2231. Min Act: -0.1700
Data Index: 5727361 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2231. Min Range: -0.2231
Max Act: 0.2231. Min Act: -0.1700
Data Index: 4552374 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2231. Min Range: -0.2231
Max Act: 0.2231. Min Act: -0.1700
Data Index: 2810216 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2231. Min Range: -0.2231
Max Act: 0.1937. Min Act: -0.1700
Data Index: 8030578 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2231. Min Range: -0.2231
Max Act: 0.1879. Min Act: -0.1700
Data Index: 2754405 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2231. Min Range: -0.2231
Max Act: 0.1822. Min Act: -0.1700
Data Index: 7905214 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2231. Min Range: -0.2231
Max Act: 0.1822. Min Act: -0.1700
Data Index: 2615937 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2231. Min Range: -0.2231
Max Act: 0.1822. Min Act: -0.1700
Data Index: 3452057 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2231. Min Range: -0.2231
Max Act: 0.1653. Min Act: -0.1700
Data Index: 3175200 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2231. Min Range: -0.2231
Max Act: 0.1765. Min Act: -0.1700
Data Index: 6185406 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2231. Min Range: -0.2231
Max Act: 0.1765. Min Act: -0.1700
Data Index: 7041024 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2231. Min Range: -0.2231
Max Act: 0.1709. Min Act: -0.1700
Data Index: 3679613 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2231. Min Range: -0.2231
Max Act: 0.1765. Min Act: -0.1700
Data Index: 5565898 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2231. Min Range: -0.2231
Max Act: 0.1653. Min Act: -0.1700
Data Index: 6716238 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2231. Min Range: -0.2231
Max Act: 0.1598. Min Act: -0.1700
Data Index: 4933674 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2231. Min Range: -0.2231
Max Act: 0.1543. Min Act: -0.1700
Data Index: 3661757 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19