Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2024 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.5459. Min Range: -4.5459
Max Act: 4.5459. Min Act: -0.1700
Data Index: 952262 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5459. Min Range: -4.5459
Max Act: 4.4209. Min Act: -0.1700
Data Index: 247539 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5459. Min Range: -4.5459
Max Act: 4.3584. Min Act: -0.1700
Data Index: 843713 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5459. Min Range: -4.5459
Max Act: 4.2646. Min Act: -0.1700
Data Index: 1345396 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5459. Min Range: -4.5459
Max Act: 4.2646. Min Act: -0.1700
Data Index: 1216431 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5459. Min Range: -4.5459
Max Act: 4.2646. Min Act: -0.1700
Data Index: 1033673 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5459. Min Range: -4.5459
Max Act: 4.2333. Min Act: -0.1700
Data Index: 35573 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5459. Min Range: -4.5459
Max Act: 4.1708. Min Act: -0.1700
Data Index: 1250594 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5459. Min Range: -4.5459
Max Act: 4.2021. Min Act: -0.1700
Data Index: 615888 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5459. Min Range: -4.5459
Max Act: 4.1396. Min Act: -0.1700
Data Index: 1247563 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5459. Min Range: -4.5459
Max Act: 4.1708. Min Act: -0.1700
Data Index: 813741 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5459. Min Range: -4.5459
Max Act: 4.2646. Min Act: -0.1700
Data Index: 868187 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5459. Min Range: -4.5459
Max Act: 4.1708. Min Act: -0.1700
Data Index: 1300914 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5459. Min Range: -4.5459
Max Act: 4.1708. Min Act: -0.1700
Data Index: 968230 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5459. Min Range: -4.5459
Max Act: 4.1396. Min Act: -0.1700
Data Index: 579546 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5459. Min Range: -4.5459
Max Act: 4.1708. Min Act: -0.1700
Data Index: 443631 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5459. Min Range: -4.5459
Max Act: 4.1396. Min Act: -0.1700
Data Index: 522413 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5459. Min Range: -4.5459
Max Act: 4.1083. Min Act: -0.1700
Data Index: 1189389 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5459. Min Range: -4.5459
Max Act: 4.1083. Min Act: -0.1700
Data Index: 411877 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5459. Min Range: -4.5459
Max Act: 4.1396. Min Act: -0.1700
Data Index: 280259 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19