Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4917 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4878. Min Range: -5.4878
Max Act: 5.4878. Min Act: -0.1700
Data Index: 6969497 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4878. Min Range: -5.4878
Max Act: 5.3316. Min Act: -0.1700
Data Index: 3689572 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4878. Min Range: -5.4878
Max Act: 5.3628. Min Act: -0.1698
Data Index: 7786447 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4878. Min Range: -5.4878
Max Act: 5.3003. Min Act: -0.1700
Data Index: 7886787 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4878. Min Range: -5.4878
Max Act: 5.3003. Min Act: -0.1698
Data Index: 5008258 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4878. Min Range: -5.4878
Max Act: 5.3003. Min Act: -0.1700
Data Index: 6738637 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4878. Min Range: -5.4878
Max Act: 5.2691. Min Act: -0.1700
Data Index: 6805672 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4878. Min Range: -5.4878
Max Act: 5.2378. Min Act: -0.1700
Data Index: 2929822 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4878. Min Range: -5.4878
Max Act: 5.2378. Min Act: -0.1700
Data Index: 5036392 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4878. Min Range: -5.4878
Max Act: 5.2378. Min Act: -0.1700
Data Index: 3687050 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4878. Min Range: -5.4878
Max Act: 5.2691. Min Act: -0.1700
Data Index: 2269489 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4878. Min Range: -5.4878
Max Act: 5.2066. Min Act: -0.1700
Data Index: 1982728 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4878. Min Range: -5.4878
Max Act: 5.2066. Min Act: -0.1700
Data Index: 7882739 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4878. Min Range: -5.4878
Max Act: 5.2066. Min Act: -0.1700
Data Index: 3354581 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4878. Min Range: -5.4878
Max Act: 5.1753. Min Act: -0.1700
Data Index: 3131612 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4878. Min Range: -5.4878
Max Act: 5.2066. Min Act: -0.1700
Data Index: 2207512 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4878. Min Range: -5.4878
Max Act: 5.1441. Min Act: -0.1700
Data Index: 2594162 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4878. Min Range: -5.4878
Max Act: 5.1753. Min Act: -0.1700
Data Index: 1832395 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4878. Min Range: -5.4878
Max Act: 5.1753. Min Act: -0.1700
Data Index: 6904459 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4878. Min Range: -5.4878
Max Act: 5.1753. Min Act: -0.1700
Data Index: 170958 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19