Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3374 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3786. Min Range: -1.3786
Max Act: 1.3786. Min Act: -0.1700
Data Index: 6636197 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3786. Min Range: -1.3786
Max Act: 1.3080. Min Act: -0.1700
Data Index: 5909958 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3786. Min Range: -1.3786
Max Act: 1.2551. Min Act: -0.1700
Data Index: 7262191 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3786. Min Range: -1.3786
Max Act: 1.2375. Min Act: -0.1697
Data Index: 4128701 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3786. Min Range: -1.3786
Max Act: 1.2198. Min Act: -0.1700
Data Index: 697663 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3786. Min Range: -1.3786
Max Act: 1.2022. Min Act: -0.1694
Data Index: 2266576 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3786. Min Range: -1.3786
Max Act: 1.2022. Min Act: -0.1700
Data Index: 1584178 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3786. Min Range: -1.3786
Max Act: 1.1846. Min Act: -0.1700
Data Index: 4010020 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3786. Min Range: -1.3786
Max Act: 1.1846. Min Act: -0.1700
Data Index: 9196 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3786. Min Range: -1.3786
Max Act: 1.1846. Min Act: -0.1663
Data Index: 7311485 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3786. Min Range: -1.3786
Max Act: 1.1846. Min Act: -0.1696
Data Index: 3681277 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3786. Min Range: -1.3786
Max Act: 1.1670. Min Act: -0.1700
Data Index: 6778368 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3786. Min Range: -1.3786
Max Act: 1.1670. Min Act: -0.1700
Data Index: 6740106 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3786. Min Range: -1.3786
Max Act: 1.1670. Min Act: -0.1695
Data Index: 4155742 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3786. Min Range: -1.3786
Max Act: 1.1670. Min Act: -0.1699
Data Index: 7563903 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3786. Min Range: -1.3786
Max Act: 1.1670. Min Act: -0.1700
Data Index: 4843256 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3786. Min Range: -1.3786
Max Act: 1.1670. Min Act: -0.1700
Data Index: 3041776 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3786. Min Range: -1.3786
Max Act: 1.1670. Min Act: -0.1700
Data Index: 1167810 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3786. Min Range: -1.3786
Max Act: 1.1494. Min Act: -0.1700
Data Index: 6283231 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3786. Min Range: -1.3786
Max Act: 1.1494. Min Act: -0.1700
Data Index: 1370104 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19