Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2896 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0616. Min Range: -4.0616
Max Act: 4.0616. Min Act: -0.1700
Data Index: 6382710 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0616. Min Range: -4.0616
Max Act: 3.9991. Min Act: -0.1700
Data Index: 3326042 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0616. Min Range: -4.0616
Max Act: 4.0303. Min Act: -0.1700
Data Index: 7369307 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0616. Min Range: -4.0616
Max Act: 3.9991. Min Act: -0.1700
Data Index: 6765580 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0616. Min Range: -4.0616
Max Act: 3.9678. Min Act: -0.1700
Data Index: 616249 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0616. Min Range: -4.0616
Max Act: 3.9991. Min Act: -0.1700
Data Index: 2815652 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0616. Min Range: -4.0616
Max Act: 3.9678. Min Act: -0.1700
Data Index: 5737948 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0616. Min Range: -4.0616
Max Act: 3.9678. Min Act: -0.1700
Data Index: 6088168 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0616. Min Range: -4.0616
Max Act: 3.9053. Min Act: -0.1700
Data Index: 7865076 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0616. Min Range: -4.0616
Max Act: 3.9365. Min Act: -0.1700
Data Index: 8125417 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0616. Min Range: -4.0616
Max Act: 3.9053. Min Act: -0.1700
Data Index: 5150179 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0616. Min Range: -4.0616
Max Act: 3.9365. Min Act: -0.1700
Data Index: 8360760 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0616. Min Range: -4.0616
Max Act: 3.9053. Min Act: -0.1700
Data Index: 5550146 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0616. Min Range: -4.0616
Max Act: 3.8740. Min Act: -0.1700
Data Index: 1861020 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0616. Min Range: -4.0616
Max Act: 3.9053. Min Act: -0.1700
Data Index: 1206943 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0616. Min Range: -4.0616
Max Act: 3.8740. Min Act: -0.1700
Data Index: 5808641 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0616. Min Range: -4.0616
Max Act: 3.9053. Min Act: -0.1700
Data Index: 3868201 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0616. Min Range: -4.0616
Max Act: 3.9053. Min Act: -0.1700
Data Index: 7148655 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0616. Min Range: -4.0616
Max Act: 3.8740. Min Act: -0.1700
Data Index: 4902970 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0616. Min Range: -4.0616
Max Act: 3.8740. Min Act: -0.1700
Data Index: 1818982 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19