Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 66 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.0671. Min Range: -6.0671
Max Act: 6.0359. Min Act: -0.1700
Data Index: 629630 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0671. Min Range: -6.0671
Max Act: 6.0359. Min Act: -0.1700
Data Index: 846552 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0671. Min Range: -6.0671
Max Act: 6.0046. Min Act: -0.1700
Data Index: 644372 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0671. Min Range: -6.0671
Max Act: 6.0046. Min Act: -0.1700
Data Index: 383707 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0671. Min Range: -6.0671
Max Act: 6.0359. Min Act: -0.1700
Data Index: 1020936 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0671. Min Range: -6.0671
Max Act: 6.0359. Min Act: -0.1700
Data Index: 1253914 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0671. Min Range: -6.0671
Max Act: 6.0671. Min Act: -0.1700
Data Index: 439428 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0671. Min Range: -6.0671
Max Act: 6.0046. Min Act: -0.1700
Data Index: 159472 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.9421. Min Act: -0.1700
Data Index: 168686 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.9421. Min Act: -0.1700
Data Index: 429856 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0671. Min Range: -6.0671
Max Act: 6.0046. Min Act: -0.1700
Data Index: 375472 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.9109. Min Act: -0.1700
Data Index: 779445 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.9734. Min Act: -0.1700
Data Index: 646199 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.9421. Min Act: -0.1700
Data Index: 384722 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.8796. Min Act: -0.1700
Data Index: 1068015 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.8796. Min Act: -0.1700
Data Index: 210386 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.9109. Min Act: -0.1700
Data Index: 603621 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.8796. Min Act: -0.1700
Data Index: 1009790 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.9109. Min Act: -0.1700
Data Index: 478560 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0671. Min Range: -6.0671
Max Act: 5.9421. Min Act: -0.1700
Data Index: 428599 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19