Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 452 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6613. Min Range: -3.6613
Max Act: 3.6613. Min Act: -0.1700
Data Index: 2676088 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6613. Min Range: -3.6613
Max Act: 3.6613. Min Act: -0.1700
Data Index: 7708917 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6613. Min Range: -3.6613
Max Act: 3.5987. Min Act: -0.1700
Data Index: 17050 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6613. Min Range: -3.6613
Max Act: 3.5674. Min Act: -0.1700
Data Index: 4363972 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6613. Min Range: -3.6613
Max Act: 3.5360. Min Act: -0.1700
Data Index: 5941703 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6613. Min Range: -3.6613
Max Act: 3.5204. Min Act: -0.1700
Data Index: 5365923 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6613. Min Range: -3.6613
Max Act: 3.5360. Min Act: -0.1700
Data Index: 7553769 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6613. Min Range: -3.6613
Max Act: 3.5204. Min Act: -0.1700
Data Index: 1906340 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6613. Min Range: -3.6613
Max Act: 3.4891. Min Act: -0.1700
Data Index: 1913545 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6613. Min Range: -3.6613
Max Act: 3.5047. Min Act: -0.1700
Data Index: 4338557 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6613. Min Range: -3.6613
Max Act: 3.5204. Min Act: -0.1700
Data Index: 3909481 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6613. Min Range: -3.6613
Max Act: 3.4891. Min Act: -0.1700
Data Index: 6758970 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6613. Min Range: -3.6613
Max Act: 3.5047. Min Act: -0.1700
Data Index: 8155251 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6613. Min Range: -3.6613
Max Act: 3.5360. Min Act: -0.1700
Data Index: 4601741 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6613. Min Range: -3.6613
Max Act: 3.5204. Min Act: -0.1700
Data Index: 6471383 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6613. Min Range: -3.6613
Max Act: 3.5047. Min Act: -0.1700
Data Index: 7041032 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6613. Min Range: -3.6613
Max Act: 3.4891. Min Act: -0.1700
Data Index: 4893962 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6613. Min Range: -3.6613
Max Act: 3.5047. Min Act: -0.1700
Data Index: 7217898 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6613. Min Range: -3.6613
Max Act: 3.4891. Min Act: -0.1700
Data Index: 1904516 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6613. Min Range: -3.6613
Max Act: 3.4734. Min Act: -0.1700
Data Index: 6901002 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19