Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3019 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8651. Min Range: -1.8651
Max Act: 1.8651. Min Act: -0.1672
Data Index: 4479077 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8651. Min Range: -1.8651
Max Act: 1.8394. Min Act: -0.1691
Data Index: 1477640 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8651. Min Range: -1.8651
Max Act: 1.7878. Min Act: -0.1700
Data Index: 3427156 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8651. Min Range: -1.8651
Max Act: 1.7706. Min Act: -0.1695
Data Index: 4479113 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8651. Min Range: -1.8651
Max Act: 1.7447. Min Act: -0.1686
Data Index: 929166 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8651. Min Range: -1.8651
Max Act: 1.7014. Min Act: -0.1700
Data Index: 2787137 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8651. Min Range: -1.8651
Max Act: 1.7101. Min Act: -0.1690
Data Index: 1477611 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8651. Min Range: -1.8651
Max Act: 1.7014. Min Act: -0.1699
Data Index: 8353429 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8651. Min Range: -1.8651
Max Act: 1.6927. Min Act: -0.1698
Data Index: 4479109 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8651. Min Range: -1.8651
Max Act: 1.6754. Min Act: -0.1700
Data Index: 1477643 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8651. Min Range: -1.8651
Max Act: 1.6754. Min Act: -0.1678
Data Index: 929165 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8651. Min Range: -1.8651
Max Act: 1.6754. Min Act: -0.1695
Data Index: 6140847 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8651. Min Range: -1.8651
Max Act: 1.6667. Min Act: -0.1694
Data Index: 6140833 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8651. Min Range: -1.8651
Max Act: 1.6754. Min Act: -0.1700
Data Index: 8372400 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8651. Min Range: -1.8651
Max Act: 1.6493. Min Act: -0.1698
Data Index: 2808089 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8651. Min Range: -1.8651
Max Act: 1.6319. Min Act: -0.1698
Data Index: 2787123 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8651. Min Range: -1.8651
Max Act: 1.6232. Min Act: -0.1699
Data Index: 1477636 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8651. Min Range: -1.8651
Max Act: 1.6319. Min Act: -0.1696
Data Index: 6140844 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8651. Min Range: -1.8651
Max Act: 1.6144. Min Act: -0.1698
Data Index: 2787139 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8651. Min Range: -1.8651
Max Act: 1.6057. Min Act: -0.1700
Data Index: 1477584 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19