Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3349 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2631. Min Range: -3.2631
Max Act: 3.2631. Min Act: -0.1700
Data Index: 3794389 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2631. Min Range: -3.2631
Max Act: 3.1531. Min Act: -0.1700
Data Index: 7961983 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2631. Min Range: -3.2631
Max Act: 3.1216. Min Act: -0.1700
Data Index: 800371 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2631. Min Range: -3.2631
Max Act: 3.0269. Min Act: -0.1700
Data Index: 7826910 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2631. Min Range: -3.2631
Max Act: 2.9953. Min Act: -0.1700
Data Index: 8432181 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2631. Min Range: -3.2631
Max Act: 2.9953. Min Act: -0.1700
Data Index: 5935389 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2631. Min Range: -3.2631
Max Act: 2.9953. Min Act: -0.1700
Data Index: 3133842 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2631. Min Range: -3.2631
Max Act: 2.9479. Min Act: -0.1700
Data Index: 8228586 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2631. Min Range: -3.2631
Max Act: 2.9479. Min Act: -0.1700
Data Index: 4162385 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2631. Min Range: -3.2631
Max Act: 2.9637. Min Act: -0.1700
Data Index: 2942982 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2631. Min Range: -3.2631
Max Act: 2.9320. Min Act: -0.1700
Data Index: 4901075 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2631. Min Range: -3.2631
Max Act: 2.9479. Min Act: -0.1700
Data Index: 7469864 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2631. Min Range: -3.2631
Max Act: 2.9479. Min Act: -0.1700
Data Index: 8037781 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2631. Min Range: -3.2631
Max Act: 2.9003. Min Act: -0.1700
Data Index: 5258036 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2631. Min Range: -3.2631
Max Act: 2.9162. Min Act: -0.1700
Data Index: 4158989 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2631. Min Range: -3.2631
Max Act: 2.9320. Min Act: -0.1700
Data Index: 1940530 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2631. Min Range: -3.2631
Max Act: 2.9003. Min Act: -0.1700
Data Index: 2441892 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2631. Min Range: -3.2631
Max Act: 2.8845. Min Act: -0.1700
Data Index: 6577583 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2631. Min Range: -3.2631
Max Act: 2.9003. Min Act: -0.1700
Data Index: 7183606 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2631. Min Range: -3.2631
Max Act: 2.9003. Min Act: -0.1700
Data Index: 5966562 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19