Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2649 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7457. Min Range: -4.7457
Max Act: 4.7457. Min Act: -0.1699
Data Index: 8431218 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7457. Min Range: -4.7457
Max Act: 4.5895. Min Act: -0.1700
Data Index: 4131517 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7457. Min Range: -4.7457
Max Act: 4.5895. Min Act: -0.1700
Data Index: 3490566 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7457. Min Range: -4.7457
Max Act: 4.5582. Min Act: -0.1694
Data Index: 4549689 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7457. Min Range: -4.7457
Max Act: 4.5582. Min Act: -0.1700
Data Index: 5380327 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7457. Min Range: -4.7457
Max Act: 4.5270. Min Act: -0.1700
Data Index: 1712332 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7457. Min Range: -4.7457
Max Act: 4.5270. Min Act: -0.1699
Data Index: 7028560 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7457. Min Range: -4.7457
Max Act: 4.5270. Min Act: -0.1700
Data Index: 6478442 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7457. Min Range: -4.7457
Max Act: 4.5270. Min Act: -0.1690
Data Index: 2945214 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7457. Min Range: -4.7457
Max Act: 4.4957. Min Act: -0.1694
Data Index: 1587923 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7457. Min Range: -4.7457
Max Act: 4.4957. Min Act: -0.1691
Data Index: 4360696 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7457. Min Range: -4.7457
Max Act: 4.4957. Min Act: -0.1697
Data Index: 8135670 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7457. Min Range: -4.7457
Max Act: 4.4957. Min Act: -0.1681
Data Index: 3470587 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7457. Min Range: -4.7457
Max Act: 4.4645. Min Act: -0.1680
Data Index: 2742046 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7457. Min Range: -4.7457
Max Act: 4.4645. Min Act: -0.1697
Data Index: 4942735 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7457. Min Range: -4.7457
Max Act: 4.4645. Min Act: -0.1699
Data Index: 6017808 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7457. Min Range: -4.7457
Max Act: 4.4645. Min Act: -0.1699
Data Index: 6150217 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7457. Min Range: -4.7457
Max Act: 4.4645. Min Act: -0.1700
Data Index: 6350890 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7457. Min Range: -4.7457
Max Act: 4.4645. Min Act: -0.1699
Data Index: 1512015 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7457. Min Range: -4.7457
Max Act: 4.4645. Min Act: -0.1700
Data Index: 7994547 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19