Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4066 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.5171. Min Range: -1.5171
Max Act: 1.5171. Min Act: -0.1699
Data Index: 758608 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5171. Min Range: -1.5171
Max Act: 1.5171. Min Act: -0.1700
Data Index: 4313173 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5171. Min Range: -1.5171
Max Act: 1.4996. Min Act: -0.1674
Data Index: 1776057 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5171. Min Range: -1.5171
Max Act: 1.5171. Min Act: -0.1691
Data Index: 3190718 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5171. Min Range: -1.5171
Max Act: 1.4820. Min Act: -0.1690
Data Index: 3391748 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5171. Min Range: -1.5171
Max Act: 1.4820. Min Act: -0.1694
Data Index: 5568298 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5171. Min Range: -1.5171
Max Act: 1.4908. Min Act: -0.1700
Data Index: 6187021 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5171. Min Range: -1.5171
Max Act: 1.4644. Min Act: -0.1696
Data Index: 5915317 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5171. Min Range: -1.5171
Max Act: 1.4556. Min Act: -0.1681
Data Index: 2271158 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5171. Min Range: -1.5171
Max Act: 1.4644. Min Act: -0.1691
Data Index: 4650684 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5171. Min Range: -1.5171
Max Act: 1.4556. Min Act: -0.1699
Data Index: 4210233 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5171. Min Range: -1.5171
Max Act: 1.4469. Min Act: -0.1559
Data Index: 3131263 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5171. Min Range: -1.5171
Max Act: 1.4469. Min Act: -0.1697
Data Index: 2094474 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5171. Min Range: -1.5171
Max Act: 1.4556. Min Act: -0.1699
Data Index: 2182631 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5171. Min Range: -1.5171
Max Act: 1.4469. Min Act: -0.1599
Data Index: 5568530 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5171. Min Range: -1.5171
Max Act: 1.4469. Min Act: -0.1691
Data Index: 6872555 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5171. Min Range: -1.5171
Max Act: 1.4644. Min Act: -0.1689
Data Index: 7466807 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5171. Min Range: -1.5171
Max Act: 1.4469. Min Act: -0.1366
Data Index: 616010 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5171. Min Range: -1.5171
Max Act: 1.4381. Min Act: -0.1674
Data Index: 6255761 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5171. Min Range: -1.5171
Max Act: 1.4469. Min Act: -0.1676
Data Index: 6076503 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19