Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1958 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1105. Min Range: -2.1105
Max Act: 2.1105. Min Act: -0.1699
Data Index: 4775891 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1105. Min Range: -2.1105
Max Act: 2.0602. Min Act: -0.1700
Data Index: 1736263 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1105. Min Range: -2.1105
Max Act: 2.0434. Min Act: -0.1698
Data Index: 4579469 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1105. Min Range: -2.1105
Max Act: 2.0181. Min Act: -0.1700
Data Index: 3162649 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1105. Min Range: -2.1105
Max Act: 2.0181. Min Act: -0.1693
Data Index: 4976178 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1105. Min Range: -2.1105
Max Act: 2.0012. Min Act: -0.1694
Data Index: 6551323 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1105. Min Range: -2.1105
Max Act: 2.0097. Min Act: -0.1700
Data Index: 6915346 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9928. Min Act: -0.1700
Data Index: 3700318 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9759. Min Act: -0.1700
Data Index: 7814970 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9843. Min Act: -0.1700
Data Index: 7851096 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9843. Min Act: -0.1700
Data Index: 7457173 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9843. Min Act: -0.1700
Data Index: 799768 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9759. Min Act: -0.1691
Data Index: 5153633 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9759. Min Act: -0.1699
Data Index: 7966900 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9759. Min Act: -0.1698
Data Index: 5153632 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9759. Min Act: -0.1700
Data Index: 832472 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9674. Min Act: -0.1700
Data Index: 6844387 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9674. Min Act: -0.1700
Data Index: 5880170 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9589. Min Act: -0.1700
Data Index: 5476412 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1105. Min Range: -2.1105
Max Act: 1.9674. Min Act: -0.1698
Data Index: 2507651 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19