Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3962 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7675. Min Range: -5.7675
Max Act: 5.7675. Min Act: -0.1700
Data Index: 2765106 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7675. Min Range: -5.7675
Max Act: 5.7362. Min Act: -0.1700
Data Index: 4381991 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7675. Min Range: -5.7675
Max Act: 5.7050. Min Act: -0.1700
Data Index: 7560077 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7675. Min Range: -5.7675
Max Act: 5.6425. Min Act: -0.1700
Data Index: 3522450 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7675. Min Range: -5.7675
Max Act: 5.5800. Min Act: -0.1700
Data Index: 6503567 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7675. Min Range: -5.7675
Max Act: 5.5800. Min Act: -0.1700
Data Index: 936203 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7675. Min Range: -5.7675
Max Act: 5.5175. Min Act: -0.1700
Data Index: 4033165 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7675. Min Range: -5.7675
Max Act: 5.5175. Min Act: -0.1700
Data Index: 2012594 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7675. Min Range: -5.7675
Max Act: 5.4862. Min Act: -0.1700
Data Index: 4651917 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7675. Min Range: -5.7675
Max Act: 5.4862. Min Act: -0.1700
Data Index: 671320 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7675. Min Range: -5.7675
Max Act: 5.4862. Min Act: -0.1700
Data Index: 1520614 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7675. Min Range: -5.7675
Max Act: 5.5175. Min Act: -0.1700
Data Index: 7122781 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7675. Min Range: -5.7675
Max Act: 5.4237. Min Act: -0.1700
Data Index: 3661627 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7675. Min Range: -5.7675
Max Act: 5.4550. Min Act: -0.1700
Data Index: 7227878 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7675. Min Range: -5.7675
Max Act: 5.4550. Min Act: -0.1700
Data Index: 6749146 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7675. Min Range: -5.7675
Max Act: 5.4550. Min Act: -0.1700
Data Index: 8372538 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7675. Min Range: -5.7675
Max Act: 5.4237. Min Act: -0.1700
Data Index: 7717728 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7675. Min Range: -5.7675
Max Act: 5.4237. Min Act: -0.1700
Data Index: 1902666 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7675. Min Range: -5.7675
Max Act: 5.4237. Min Act: -0.1700
Data Index: 3219126 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7675. Min Range: -5.7675
Max Act: 5.4237. Min Act: -0.1700
Data Index: 3035470 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19