Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2021 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8246. Min Range: -3.8246
Max Act: 3.8246. Min Act: -0.1700
Data Index: 335697 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8246. Min Range: -3.8246
Max Act: 3.8246. Min Act: -0.1700
Data Index: 5574787 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8246. Min Range: -3.8246
Max Act: 3.8246. Min Act: -0.1700
Data Index: 4008694 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8246. Min Range: -3.8246
Max Act: 3.8246. Min Act: -0.1700
Data Index: 2299198 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8246. Min Range: -3.8246
Max Act: 3.8246. Min Act: -0.1700
Data Index: 6978528 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8246. Min Range: -3.8246
Max Act: 3.7933. Min Act: -0.1700
Data Index: 693845 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8246. Min Range: -3.8246
Max Act: 3.7777. Min Act: -0.1700
Data Index: 3243693 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8246. Min Range: -3.8246
Max Act: 3.7464. Min Act: -0.1700
Data Index: 3428700 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8246. Min Range: -3.8246
Max Act: 3.7464. Min Act: -0.1700
Data Index: 6279937 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8246. Min Range: -3.8246
Max Act: 3.7308. Min Act: -0.1700
Data Index: 964664 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8246. Min Range: -3.8246
Max Act: 3.7464. Min Act: -0.1700
Data Index: 3707871 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8246. Min Range: -3.8246
Max Act: 3.7308. Min Act: -0.1700
Data Index: 3962124 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8246. Min Range: -3.8246
Max Act: 3.7308. Min Act: -0.1700
Data Index: 5758657 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8246. Min Range: -3.8246
Max Act: 3.7151. Min Act: -0.1700
Data Index: 7472601 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8246. Min Range: -3.8246
Max Act: 3.6682. Min Act: -0.1700
Data Index: 4880193 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8246. Min Range: -3.8246
Max Act: 3.6995. Min Act: -0.1700
Data Index: 2530735 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8246. Min Range: -3.8246
Max Act: 3.6995. Min Act: -0.1700
Data Index: 6226113 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8246. Min Range: -3.8246
Max Act: 3.6682. Min Act: -0.1700
Data Index: 2069998 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8246. Min Range: -3.8246
Max Act: 3.6682. Min Act: -0.1700
Data Index: 2659840 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8246. Min Range: -3.8246
Max Act: 3.6838. Min Act: -0.1700
Data Index: 4445276 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19