Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1441 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.3175. Min Act: -0.1700
Data Index: 5295516 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.2550. Min Act: -0.1700
Data Index: 80262 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.2237. Min Act: -0.1700
Data Index: 6826247 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.1612. Min Act: -0.1700
Data Index: 7868727 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.1300. Min Act: -0.1700
Data Index: 6139322 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.1300. Min Act: -0.1700
Data Index: 5865772 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.0675. Min Act: -0.1700
Data Index: 2862298 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.0362. Min Act: -0.1700
Data Index: 8169468 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.0362. Min Act: -0.1700
Data Index: 3633805 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.0987. Min Act: -0.1700
Data Index: 6859701 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.0362. Min Act: -0.1700
Data Index: 5784682 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.0050. Min Act: -0.1700
Data Index: 1869354 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.0362. Min Act: -0.1700
Data Index: 7510067 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.0050. Min Act: -0.1700
Data Index: 8498268 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.0362. Min Act: -0.1700
Data Index: 3273041 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.0050. Min Act: -0.1700
Data Index: 7075162 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.0362. Min Act: -0.1700
Data Index: 4818956 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3175. Min Range: -5.3175
Max Act: 4.9737. Min Act: -0.1700
Data Index: 8754129 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3175. Min Range: -5.3175
Max Act: 4.9737. Min Act: -0.1700
Data Index: 1024568 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3175. Min Range: -5.3175
Max Act: 4.9737. Min Act: -0.1700
Data Index: 1067674 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19