Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 609 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1212. Min Range: -5.1212
Max Act: 5.1212. Min Act: -0.1700
Data Index: 4206135 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1212. Min Range: -5.1212
Max Act: 4.9649. Min Act: -0.1700
Data Index: 3151558 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1212. Min Range: -5.1212
Max Act: 4.9024. Min Act: -0.1700
Data Index: 4543145 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1212. Min Range: -5.1212
Max Act: 4.7149. Min Act: -0.1700
Data Index: 4798131 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1212. Min Range: -5.1212
Max Act: 4.6837. Min Act: -0.1700
Data Index: 5756700 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1212. Min Range: -5.1212
Max Act: 4.6837. Min Act: -0.1700
Data Index: 1602482 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1212. Min Range: -5.1212
Max Act: 4.5899. Min Act: -0.1700
Data Index: 645448 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1212. Min Range: -5.1212
Max Act: 4.6212. Min Act: -0.1700
Data Index: 422190 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1212. Min Range: -5.1212
Max Act: 4.5899. Min Act: -0.1700
Data Index: 2698737 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1212. Min Range: -5.1212
Max Act: 4.5587. Min Act: -0.1700
Data Index: 1591179 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1212. Min Range: -5.1212
Max Act: 4.5587. Min Act: -0.1700
Data Index: 4247036 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1212. Min Range: -5.1212
Max Act: 4.5587. Min Act: -0.1700
Data Index: 6122972 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1212. Min Range: -5.1212
Max Act: 4.4962. Min Act: -0.1700
Data Index: 1935619 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1212. Min Range: -5.1212
Max Act: 4.5274. Min Act: -0.1700
Data Index: 7561699 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1212. Min Range: -5.1212
Max Act: 4.4962. Min Act: -0.1700
Data Index: 156493 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1212. Min Range: -5.1212
Max Act: 4.4649. Min Act: -0.1700
Data Index: 5646446 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1212. Min Range: -5.1212
Max Act: 4.4962. Min Act: -0.1700
Data Index: 6128824 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1212. Min Range: -5.1212
Max Act: 4.4649. Min Act: -0.1700
Data Index: 5055903 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1212. Min Range: -5.1212
Max Act: 4.4649. Min Act: -0.1700
Data Index: 2634645 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1212. Min Range: -5.1212
Max Act: 4.4649. Min Act: -0.1700
Data Index: 4044000 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19