Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 185 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9784. Min Range: -4.9784
Max Act: 4.9784. Min Act: -0.1700
Data Index: 181438 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9784. Min Range: -4.9784
Max Act: 4.8221. Min Act: -0.1700
Data Index: 268471 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9784. Min Range: -4.9784
Max Act: 4.8221. Min Act: -0.1700
Data Index: 1077351 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9784. Min Range: -4.9784
Max Act: 4.8221. Min Act: -0.1700
Data Index: 585044 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9784. Min Range: -4.9784
Max Act: 4.7596. Min Act: -0.1700
Data Index: 628632 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9784. Min Range: -4.9784
Max Act: 4.7909. Min Act: -0.1700
Data Index: 824476 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9784. Min Range: -4.9784
Max Act: 4.7596. Min Act: -0.1700
Data Index: 58532 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9784. Min Range: -4.9784
Max Act: 4.7596. Min Act: -0.1700
Data Index: 843469 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9784. Min Range: -4.9784
Max Act: 4.7283. Min Act: -0.1700
Data Index: 89420 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9784. Min Range: -4.9784
Max Act: 4.7596. Min Act: -0.1700
Data Index: 1105326 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9784. Min Range: -4.9784
Max Act: 4.7909. Min Act: -0.1700
Data Index: 136795 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9784. Min Range: -4.9784
Max Act: 4.7596. Min Act: -0.1700
Data Index: 1344668 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9784. Min Range: -4.9784
Max Act: 4.7283. Min Act: -0.1700
Data Index: 361463 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9784. Min Range: -4.9784
Max Act: 4.7283. Min Act: -0.1700
Data Index: 83128 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9784. Min Range: -4.9784
Max Act: 4.7596. Min Act: -0.1700
Data Index: 303257 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9784. Min Range: -4.9784
Max Act: 4.7596. Min Act: -0.1700
Data Index: 17513 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9784. Min Range: -4.9784
Max Act: 4.7283. Min Act: -0.1700
Data Index: 60853 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9784. Min Range: -4.9784
Max Act: 4.7283. Min Act: -0.1700
Data Index: 348670 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9784. Min Range: -4.9784
Max Act: 4.7909. Min Act: -0.1700
Data Index: 1271129 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9784. Min Range: -4.9784
Max Act: 4.7596. Min Act: -0.1700
Data Index: 268408 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19