Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1486 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.2437. Min Act: -0.1700
Data Index: 538096 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.2749. Min Act: -0.1700
Data Index: 317013 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.2437. Min Act: -0.1699
Data Index: 308485 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.2124. Min Act: -0.1700
Data Index: 1238044 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.1499. Min Act: -0.1699
Data Index: 727351 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.1812. Min Act: -0.1700
Data Index: 326033 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.1499. Min Act: -0.1700
Data Index: 938841 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.1812. Min Act: -0.1700
Data Index: 443802 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.1187. Min Act: -0.1700
Data Index: 759313 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.1812. Min Act: -0.1700
Data Index: 1142816 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.1499. Min Act: -0.1700
Data Index: 405411 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.1187. Min Act: -0.1700
Data Index: 620187 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.1499. Min Act: -0.1700
Data Index: 300135 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.1499. Min Act: -0.1700
Data Index: 791857 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.1187. Min Act: -0.1700
Data Index: 740548 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.1499. Min Act: -0.1700
Data Index: 705536 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.0874. Min Act: -0.1700
Data Index: 627331 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.0874. Min Act: -0.1699
Data Index: 1006336 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.0874. Min Act: -0.1700
Data Index: 808566 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.0874. Min Act: -0.1700
Data Index: 284227 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19