Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2875 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.5695. Min Range: -0.5695
Max Act: 0.5695. Min Act: -0.1700
Data Index: 1561073 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5695. Min Range: -0.5695
Max Act: 0.5695. Min Act: -0.1665
Data Index: 6823521 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5695. Min Range: -0.5695
Max Act: 0.5695. Min Act: -0.1667
Data Index: 6039485 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5695. Min Range: -0.5695
Max Act: 0.5695. Min Act: -0.1700
Data Index: 2753426 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5695. Min Range: -0.5695
Max Act: 0.5695. Min Act: -0.1699
Data Index: 711527 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5695. Min Range: -0.5695
Max Act: 0.5695. Min Act: -0.1697
Data Index: 4395495 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5695. Min Range: -0.5695
Max Act: 0.5695. Min Act: -0.1606
Data Index: 1623788 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5695. Min Range: -0.5695
Max Act: 0.5695. Min Act: -0.1700
Data Index: 2843471 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5695. Min Range: -0.5695
Max Act: 0.5695. Min Act: -0.1695
Data Index: 5918071 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5695. Min Range: -0.5695
Max Act: 0.5695. Min Act: -0.1680
Data Index: 4109128 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5695. Min Range: -0.5695
Max Act: 0.5695. Min Act: -0.1699
Data Index: 1870495 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5695. Min Range: -0.5695
Max Act: 0.5695. Min Act: -0.1700
Data Index: 3581867 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5695. Min Range: -0.5695
Max Act: 0.5695. Min Act: -0.1698
Data Index: 595381 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5695. Min Range: -0.5695
Max Act: 0.5695. Min Act: -0.1685
Data Index: 5466306 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5695. Min Range: -0.5695
Max Act: 0.5695. Min Act: -0.1675
Data Index: 5414579 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5695. Min Range: -0.5695
Max Act: 0.5695. Min Act: -0.1696
Data Index: 2461017 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5695. Min Range: -0.5695
Max Act: 0.5695. Min Act: -0.1700
Data Index: 445802 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5695. Min Range: -0.5695
Max Act: 0.5695. Min Act: -0.1696
Data Index: 3651830 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5695. Min Range: -0.5695
Max Act: 0.5695. Min Act: -0.1699
Data Index: 4580969 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5695. Min Range: -0.5695
Max Act: 0.5695. Min Act: -0.1700
Data Index: 5014161 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19