Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3394 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4964. Min Range: -6.4964
Max Act: 6.4964. Min Act: -0.1700
Data Index: 8530395 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4964. Min Range: -6.4964
Max Act: 6.1526. Min Act: -0.1700
Data Index: 6849324 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4964. Min Range: -6.4964
Max Act: 6.0276. Min Act: -0.1700
Data Index: 6163958 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4964. Min Range: -6.4964
Max Act: 6.0589. Min Act: -0.1700
Data Index: 3689360 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4964. Min Range: -6.4964
Max Act: 6.0589. Min Act: -0.1700
Data Index: 4245778 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4964. Min Range: -6.4964
Max Act: 6.0276. Min Act: -0.1700
Data Index: 6036869 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4964. Min Range: -6.4964
Max Act: 5.9964. Min Act: -0.1700
Data Index: 7534800 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4964. Min Range: -6.4964
Max Act: 5.9651. Min Act: -0.1700
Data Index: 7310896 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4964. Min Range: -6.4964
Max Act: 5.9339. Min Act: -0.1700
Data Index: 6009760 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4964. Min Range: -6.4964
Max Act: 5.9339. Min Act: -0.1700
Data Index: 1834852 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4964. Min Range: -6.4964
Max Act: 5.9339. Min Act: -0.1700
Data Index: 6500841 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4964. Min Range: -6.4964
Max Act: 5.8714. Min Act: -0.1700
Data Index: 3172921 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4964. Min Range: -6.4964
Max Act: 5.8401. Min Act: -0.1700
Data Index: 4189016 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4964. Min Range: -6.4964
Max Act: 5.8401. Min Act: -0.1700
Data Index: 1538179 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4964. Min Range: -6.4964
Max Act: 5.8401. Min Act: -0.1700
Data Index: 8542723 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4964. Min Range: -6.4964
Max Act: 5.8089. Min Act: -0.1700
Data Index: 8214180 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4964. Min Range: -6.4964
Max Act: 5.8089. Min Act: -0.1700
Data Index: 1657186 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4964. Min Range: -6.4964
Max Act: 5.8401. Min Act: -0.1700
Data Index: 3108661 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4964. Min Range: -6.4964
Max Act: 5.7776. Min Act: -0.1700
Data Index: 1337926 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4964. Min Range: -6.4964
Max Act: 5.7776. Min Act: -0.1700
Data Index: 2443791 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19