Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5618 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1706. Min Range: -2.1706
Max Act: 2.1706. Min Act: -0.1700
Data Index: 5798353 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1706. Min Range: -2.1706
Max Act: 2.1539. Min Act: -0.1700
Data Index: 8775589 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1706. Min Range: -2.1706
Max Act: 2.1372. Min Act: -0.1700
Data Index: 2254833 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1706. Min Range: -2.1706
Max Act: 2.1038. Min Act: -0.1700
Data Index: 6732864 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1706. Min Range: -2.1706
Max Act: 2.1205. Min Act: -0.1700
Data Index: 1089381 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1706. Min Range: -2.1706
Max Act: 2.1205. Min Act: -0.1700
Data Index: 7737457 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1706. Min Range: -2.1706
Max Act: 2.1038. Min Act: -0.1700
Data Index: 1937069 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1706. Min Range: -2.1706
Max Act: 2.1038. Min Act: -0.1700
Data Index: 6587720 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1706. Min Range: -2.1706
Max Act: 2.1038. Min Act: -0.1700
Data Index: 8052978 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1706. Min Range: -2.1706
Max Act: 2.1038. Min Act: -0.1700
Data Index: 5314391 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1706. Min Range: -2.1706
Max Act: 2.0871. Min Act: -0.1700
Data Index: 2779415 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1706. Min Range: -2.1706
Max Act: 2.0871. Min Act: -0.1700
Data Index: 4712643 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1706. Min Range: -2.1706
Max Act: 2.0703. Min Act: -0.1700
Data Index: 7667503 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1706. Min Range: -2.1706
Max Act: 2.0871. Min Act: -0.1700
Data Index: 1836756 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1706. Min Range: -2.1706
Max Act: 2.0871. Min Act: -0.1700
Data Index: 3419409 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1706. Min Range: -2.1706
Max Act: 2.0703. Min Act: -0.1700
Data Index: 4496635 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1706. Min Range: -2.1706
Max Act: 2.0703. Min Act: -0.1700
Data Index: 551207 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1706. Min Range: -2.1706
Max Act: 2.0703. Min Act: -0.1700
Data Index: 2696680 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1706. Min Range: -2.1706
Max Act: 2.0703. Min Act: -0.1700
Data Index: 4512966 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1706. Min Range: -2.1706
Max Act: 2.0535. Min Act: -0.1700
Data Index: 5559185 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19