Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1866 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.2025. Min Range: -2.2025
Max Act: 2.2025. Min Act: -0.1700
Data Index: 933289 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2025. Min Range: -2.2025
Max Act: 2.1693. Min Act: -0.1700
Data Index: 1211461 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2025. Min Range: -2.2025
Max Act: 2.1526. Min Act: -0.1700
Data Index: 1270686 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2025. Min Range: -2.2025
Max Act: 2.1693. Min Act: -0.1700
Data Index: 1209579 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2025. Min Range: -2.2025
Max Act: 2.1360. Min Act: -0.1700
Data Index: 1642250 (Python Code)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2025. Min Range: -2.2025
Max Act: 2.1526. Min Act: -0.1700
Data Index: 409529 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2025. Min Range: -2.2025
Max Act: 2.1193. Min Act: -0.1700
Data Index: 1149444 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2025. Min Range: -2.2025
Max Act: 2.1193. Min Act: -0.1700
Data Index: 397635 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2025. Min Range: -2.2025
Max Act: 2.1193. Min Act: -0.1700
Data Index: 517484 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2025. Min Range: -2.2025
Max Act: 2.1193. Min Act: -0.1700
Data Index: 1179145 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2025. Min Range: -2.2025
Max Act: 2.1193. Min Act: -0.1700
Data Index: 1186915 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2025. Min Range: -2.2025
Max Act: 2.1193. Min Act: -0.1700
Data Index: 574458 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2025. Min Range: -2.2025
Max Act: 2.1026. Min Act: -0.1700
Data Index: 1181122 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2025. Min Range: -2.2025
Max Act: 2.1193. Min Act: -0.1700
Data Index: 171473 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2025. Min Range: -2.2025
Max Act: 2.0858. Min Act: -0.1700
Data Index: 677502 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2025. Min Range: -2.2025
Max Act: 2.0858. Min Act: -0.1700
Data Index: 1203525 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2025. Min Range: -2.2025
Max Act: 2.0858. Min Act: -0.1700
Data Index: 372575 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2025. Min Range: -2.2025
Max Act: 2.1026. Min Act: -0.1700
Data Index: 1224562 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2025. Min Range: -2.2025
Max Act: 2.0858. Min Act: -0.1700
Data Index: 528676 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2025. Min Range: -2.2025
Max Act: 2.0858. Min Act: -0.1700
Data Index: 302825 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19