Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4048 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7672. Min Range: -1.7672
Max Act: 1.7672. Min Act: -0.1700
Data Index: 6524642 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7672. Min Range: -1.7672
Max Act: 1.7586. Min Act: -0.1700
Data Index: 5614798 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7672. Min Range: -1.7672
Max Act: 1.7413. Min Act: -0.1700
Data Index: 7876982 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7672. Min Range: -1.7672
Max Act: 1.7240. Min Act: -0.1700
Data Index: 5932805 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7672. Min Range: -1.7672
Max Act: 1.7240. Min Act: -0.1700
Data Index: 2539305 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7672. Min Range: -1.7672
Max Act: 1.7240. Min Act: -0.1700
Data Index: 1667551 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7672. Min Range: -1.7672
Max Act: 1.7327. Min Act: -0.1700
Data Index: 7654107 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7672. Min Range: -1.7672
Max Act: 1.7154. Min Act: -0.1700
Data Index: 3570989 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7672. Min Range: -1.7672
Max Act: 1.6894. Min Act: -0.1700
Data Index: 1014472 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7672. Min Range: -1.7672
Max Act: 1.6981. Min Act: -0.1700
Data Index: 5128463 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7672. Min Range: -1.7672
Max Act: 1.6981. Min Act: -0.1700
Data Index: 5480878 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7672. Min Range: -1.7672
Max Act: 1.6894. Min Act: -0.1700
Data Index: 4396780 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7672. Min Range: -1.7672
Max Act: 1.6894. Min Act: -0.1700
Data Index: 3110694 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7672. Min Range: -1.7672
Max Act: 1.6807. Min Act: -0.1700
Data Index: 2484581 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7672. Min Range: -1.7672
Max Act: 1.6720. Min Act: -0.1692
Data Index: 438092 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7672. Min Range: -1.7672
Max Act: 1.6633. Min Act: -0.1700
Data Index: 7076625 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7672. Min Range: -1.7672
Max Act: 1.6633. Min Act: -0.1700
Data Index: 3800671 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7672. Min Range: -1.7672
Max Act: 1.6633. Min Act: -0.1700
Data Index: 379293 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7672. Min Range: -1.7672
Max Act: 1.6633. Min Act: -0.1698
Data Index: 5185259 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7672. Min Range: -1.7672
Max Act: 1.6720. Min Act: -0.1691
Data Index: 4721890 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19