Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3180 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0616. Min Range: -5.0616
Max Act: 5.0616. Min Act: -0.1700
Data Index: 8359673 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0616. Min Range: -5.0616
Max Act: 4.8741. Min Act: -0.1700
Data Index: 7464096 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0616. Min Range: -5.0616
Max Act: 4.8429. Min Act: -0.1700
Data Index: 5509237 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0616. Min Range: -5.0616
Max Act: 4.7491. Min Act: -0.1700
Data Index: 8681199 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0616. Min Range: -5.0616
Max Act: 4.7179. Min Act: -0.1700
Data Index: 3932672 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0616. Min Range: -5.0616
Max Act: 4.7179. Min Act: -0.1700
Data Index: 7845289 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0616. Min Range: -5.0616
Max Act: 4.6866. Min Act: -0.1700
Data Index: 1083442 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0616. Min Range: -5.0616
Max Act: 4.6866. Min Act: -0.1700
Data Index: 8824129 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0616. Min Range: -5.0616
Max Act: 4.6866. Min Act: -0.1700
Data Index: 1834686 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0616. Min Range: -5.0616
Max Act: 4.6866. Min Act: -0.1700
Data Index: 2338797 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0616. Min Range: -5.0616
Max Act: 4.6866. Min Act: -0.1700
Data Index: 2047837 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0616. Min Range: -5.0616
Max Act: 4.6866. Min Act: -0.1700
Data Index: 7234683 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0616. Min Range: -5.0616
Max Act: 4.6554. Min Act: -0.1700
Data Index: 6116950 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0616. Min Range: -5.0616
Max Act: 4.6554. Min Act: -0.1700
Data Index: 1167623 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0616. Min Range: -5.0616
Max Act: 4.6554. Min Act: -0.1700
Data Index: 4045322 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0616. Min Range: -5.0616
Max Act: 4.6554. Min Act: -0.1700
Data Index: 7001613 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0616. Min Range: -5.0616
Max Act: 4.6241. Min Act: -0.1700
Data Index: 725293 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0616. Min Range: -5.0616
Max Act: 4.6241. Min Act: -0.1700
Data Index: 4294478 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0616. Min Range: -5.0616
Max Act: 4.6241. Min Act: -0.1700
Data Index: 5373356 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0616. Min Range: -5.0616
Max Act: 4.6241. Min Act: -0.1700
Data Index: 5390715 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19