Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3698 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7158. Min Range: -8.7158
Max Act: 8.7158. Min Act: -0.1700
Data Index: 3172608 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7158. Min Range: -8.7158
Max Act: 8.7158. Min Act: -0.1700
Data Index: 4884641 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7158. Min Range: -8.7158
Max Act: 8.6533. Min Act: -0.1700
Data Index: 777814 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7158. Min Range: -8.7158
Max Act: 8.5908. Min Act: -0.1700
Data Index: 4434626 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7158. Min Range: -8.7158
Max Act: 8.5283. Min Act: -0.1700
Data Index: 2360483 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7158. Min Range: -8.7158
Max Act: 8.4658. Min Act: -0.1700
Data Index: 3367025 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7158. Min Range: -8.7158
Max Act: 8.4658. Min Act: -0.1700
Data Index: 3407992 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7158. Min Range: -8.7158
Max Act: 8.5283. Min Act: -0.1700
Data Index: 3544328 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7158. Min Range: -8.7158
Max Act: 8.5283. Min Act: -0.1700
Data Index: 1677938 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7158. Min Range: -8.7158
Max Act: 8.4033. Min Act: -0.1700
Data Index: 5878989 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7158. Min Range: -8.7158
Max Act: 8.4658. Min Act: -0.1700
Data Index: 7009383 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7158. Min Range: -8.7158
Max Act: 8.4033. Min Act: -0.1700
Data Index: 2061131 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7158. Min Range: -8.7158
Max Act: 8.3408. Min Act: -0.1700
Data Index: 2379484 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7158. Min Range: -8.7158
Max Act: 8.4033. Min Act: -0.1700
Data Index: 6884407 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7158. Min Range: -8.7158
Max Act: 8.3408. Min Act: -0.1700
Data Index: 3476 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7158. Min Range: -8.7158
Max Act: 8.4033. Min Act: -0.1700
Data Index: 3058223 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7158. Min Range: -8.7158
Max Act: 8.4033. Min Act: -0.1700
Data Index: 5942068 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7158. Min Range: -8.7158
Max Act: 8.3408. Min Act: -0.1700
Data Index: 1625564 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7158. Min Range: -8.7158
Max Act: 8.3408. Min Act: -0.1700
Data Index: 3024487 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7158. Min Range: -8.7158
Max Act: 8.3408. Min Act: -0.1700
Data Index: 3076080 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19