Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 918 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1089. Min Range: -5.1089
Max Act: 5.1089. Min Act: -0.1700
Data Index: 4783005 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1089. Min Range: -5.1089
Max Act: 5.0776. Min Act: -0.1700
Data Index: 1526226 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1089. Min Range: -5.1089
Max Act: 5.1089. Min Act: -0.1700
Data Index: 907198 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1089. Min Range: -5.1089
Max Act: 5.0464. Min Act: -0.1700
Data Index: 6933562 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1089. Min Range: -5.1089
Max Act: 5.0776. Min Act: -0.1700
Data Index: 3268717 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1089. Min Range: -5.1089
Max Act: 5.0464. Min Act: -0.1700
Data Index: 1501749 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1089. Min Range: -5.1089
Max Act: 5.0776. Min Act: -0.1700
Data Index: 2658297 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1089. Min Range: -5.1089
Max Act: 5.0776. Min Act: -0.1700
Data Index: 5116630 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1089. Min Range: -5.1089
Max Act: 5.0464. Min Act: -0.1700
Data Index: 403355 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1089. Min Range: -5.1089
Max Act: 5.0464. Min Act: -0.1700
Data Index: 3287536 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1089. Min Range: -5.1089
Max Act: 5.0151. Min Act: -0.1700
Data Index: 2409330 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1089. Min Range: -5.1089
Max Act: 5.0464. Min Act: -0.1700
Data Index: 5558229 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1089. Min Range: -5.1089
Max Act: 5.0464. Min Act: -0.1700
Data Index: 5297006 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1089. Min Range: -5.1089
Max Act: 5.0464. Min Act: -0.1700
Data Index: 1601778 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1089. Min Range: -5.1089
Max Act: 5.0776. Min Act: -0.1700
Data Index: 1537080 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1089. Min Range: -5.1089
Max Act: 5.0776. Min Act: -0.1700
Data Index: 814299 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1089. Min Range: -5.1089
Max Act: 5.0151. Min Act: -0.1700
Data Index: 3400514 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1089. Min Range: -5.1089
Max Act: 5.0151. Min Act: -0.1700
Data Index: 557099 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1089. Min Range: -5.1089
Max Act: 5.0151. Min Act: -0.1700
Data Index: 4871712 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1089. Min Range: -5.1089
Max Act: 5.0464. Min Act: -0.1700
Data Index: 624444 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19