Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 926 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5729. Min Range: -1.5729
Max Act: 1.5729. Min Act: -0.1700
Data Index: 4797124 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5729. Min Range: -1.5729
Max Act: 1.4852. Min Act: -0.1700
Data Index: 6517490 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5729. Min Range: -1.5729
Max Act: 1.4588. Min Act: -0.1700
Data Index: 430355 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5729. Min Range: -1.5729
Max Act: 1.4588. Min Act: -0.1700
Data Index: 197490 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5729. Min Range: -1.5729
Max Act: 1.4588. Min Act: -0.1700
Data Index: 8224306 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5729. Min Range: -1.5729
Max Act: 1.4324. Min Act: -0.1700
Data Index: 6733642 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5729. Min Range: -1.5729
Max Act: 1.4324. Min Act: -0.1700
Data Index: 4116963 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5729. Min Range: -1.5729
Max Act: 1.4104. Min Act: -0.1700
Data Index: 4558301 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5729. Min Range: -1.5729
Max Act: 1.3752. Min Act: -0.1700
Data Index: 1773638 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5729. Min Range: -1.5729
Max Act: 1.4016. Min Act: -0.1700
Data Index: 8768444 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5729. Min Range: -1.5729
Max Act: 1.3972. Min Act: -0.1700
Data Index: 3540168 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5729. Min Range: -1.5729
Max Act: 1.3972. Min Act: -0.1700
Data Index: 5815292 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5729. Min Range: -1.5729
Max Act: 1.3972. Min Act: -0.1700
Data Index: 2349069 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5729. Min Range: -1.5729
Max Act: 1.3928. Min Act: -0.1700
Data Index: 8045146 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5729. Min Range: -1.5729
Max Act: 1.3928. Min Act: -0.1700
Data Index: 2057980 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5729. Min Range: -1.5729
Max Act: 1.3972. Min Act: -0.1700
Data Index: 345515 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5729. Min Range: -1.5729
Max Act: 1.3884. Min Act: -0.1700
Data Index: 3077695 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5729. Min Range: -1.5729
Max Act: 1.3884. Min Act: -0.1700
Data Index: 2937263 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5729. Min Range: -1.5729
Max Act: 1.3884. Min Act: -0.1700
Data Index: 3033464 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5729. Min Range: -1.5729
Max Act: 1.3884. Min Act: -0.1700
Data Index: 3232406 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19