Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2306 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.6201. Min Act: -0.1700
Data Index: 1276833 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.6514. Min Act: -0.1700
Data Index: 6891010 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.6201. Min Act: -0.1700
Data Index: 4081127 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.6201. Min Act: -0.1700
Data Index: 8063649 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5576. Min Act: -0.1700
Data Index: 2933337 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5889. Min Act: -0.1700
Data Index: 8319143 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5889. Min Act: -0.1700
Data Index: 6149700 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5576. Min Act: -0.1700
Data Index: 1005750 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.6201. Min Act: -0.1700
Data Index: 8298950 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5889. Min Act: -0.1700
Data Index: 7973593 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5889. Min Act: -0.1700
Data Index: 3418808 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5889. Min Act: -0.1700
Data Index: 3418809 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5576. Min Act: -0.1700
Data Index: 5716282 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5576. Min Act: -0.1700
Data Index: 3848727 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5576. Min Act: -0.1700
Data Index: 7100934 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5264. Min Act: -0.1700
Data Index: 7342585 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5264. Min Act: -0.1700
Data Index: 575229 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5264. Min Act: -0.1700
Data Index: 1240837 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5264. Min Act: -0.1700
Data Index: 6049567 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5264. Min Act: -0.1700
Data Index: 345235 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19