Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1555 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8773. Min Range: -3.8773
Max Act: 3.8773. Min Act: -0.1700
Data Index: 4063574 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8773. Min Range: -3.8773
Max Act: 3.7523. Min Act: -0.1700
Data Index: 4463426 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8773. Min Range: -3.8773
Max Act: 3.7210. Min Act: -0.1700
Data Index: 5908563 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8773. Min Range: -3.8773
Max Act: 3.7366. Min Act: -0.1700
Data Index: 5457977 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8773. Min Range: -3.8773
Max Act: 3.7210. Min Act: -0.1700
Data Index: 942043 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8773. Min Range: -3.8773
Max Act: 3.6897. Min Act: -0.1700
Data Index: 7052619 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8773. Min Range: -3.8773
Max Act: 3.6584. Min Act: -0.1700
Data Index: 5231751 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8773. Min Range: -3.8773
Max Act: 3.6584. Min Act: -0.1700
Data Index: 5420724 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8773. Min Range: -3.8773
Max Act: 3.6740. Min Act: -0.1700
Data Index: 5147500 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8773. Min Range: -3.8773
Max Act: 3.6115. Min Act: -0.1700
Data Index: 3973692 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8773. Min Range: -3.8773
Max Act: 3.6115. Min Act: -0.1700
Data Index: 4054761 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8773. Min Range: -3.8773
Max Act: 3.6271. Min Act: -0.1700
Data Index: 7018922 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8773. Min Range: -3.8773
Max Act: 3.5958. Min Act: -0.1700
Data Index: 3538565 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8773. Min Range: -3.8773
Max Act: 3.6115. Min Act: -0.1700
Data Index: 5324460 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8773. Min Range: -3.8773
Max Act: 3.6115. Min Act: -0.1700
Data Index: 6796538 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8773. Min Range: -3.8773
Max Act: 3.5801. Min Act: -0.1700
Data Index: 6773754 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8773. Min Range: -3.8773
Max Act: 3.5801. Min Act: -0.1700
Data Index: 222139 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8773. Min Range: -3.8773
Max Act: 3.5645. Min Act: -0.1700
Data Index: 4728420 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8773. Min Range: -3.8773
Max Act: 3.5801. Min Act: -0.1700
Data Index: 3273255 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8773. Min Range: -3.8773
Max Act: 3.5488. Min Act: -0.1700
Data Index: 1550860 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19