Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3068 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7624. Min Range: -4.7624
Max Act: 4.7624. Min Act: -0.1700
Data Index: 2759591 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7624. Min Range: -4.7624
Max Act: 4.6374. Min Act: -0.1700
Data Index: 2442281 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7624. Min Range: -4.7624
Max Act: 4.6374. Min Act: -0.1700
Data Index: 7887602 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7624. Min Range: -4.7624
Max Act: 4.6062. Min Act: -0.1700
Data Index: 1679769 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7624. Min Range: -4.7624
Max Act: 4.5749. Min Act: -0.1700
Data Index: 2410998 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7624. Min Range: -4.7624
Max Act: 4.5749. Min Act: -0.1700
Data Index: 6810264 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7624. Min Range: -4.7624
Max Act: 4.5124. Min Act: -0.1700
Data Index: 2950692 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7624. Min Range: -4.7624
Max Act: 4.5124. Min Act: -0.1700
Data Index: 1292053 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7624. Min Range: -4.7624
Max Act: 4.4812. Min Act: -0.1700
Data Index: 147392 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7624. Min Range: -4.7624
Max Act: 4.5124. Min Act: -0.1700
Data Index: 4128574 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7624. Min Range: -4.7624
Max Act: 4.4812. Min Act: -0.1700
Data Index: 343148 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7624. Min Range: -4.7624
Max Act: 4.4499. Min Act: -0.1700
Data Index: 7792742 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7624. Min Range: -4.7624
Max Act: 4.4499. Min Act: -0.1700
Data Index: 1852719 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7624. Min Range: -4.7624
Max Act: 4.4499. Min Act: -0.1700
Data Index: 157720 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7624. Min Range: -4.7624
Max Act: 4.3874. Min Act: -0.1700
Data Index: 1850983 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7624. Min Range: -4.7624
Max Act: 4.4187. Min Act: -0.1700
Data Index: 3658255 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7624. Min Range: -4.7624
Max Act: 4.3874. Min Act: -0.1700
Data Index: 2930146 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7624. Min Range: -4.7624
Max Act: 4.4187. Min Act: -0.1700
Data Index: 5536982 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7624. Min Range: -4.7624
Max Act: 4.3874. Min Act: -0.1700
Data Index: 3377514 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7624. Min Range: -4.7624
Max Act: 4.4187. Min Act: -0.1700
Data Index: 3109560 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19