Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3614 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1349119 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.3010. Min Act: -0.0000

Data Index: 424604 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.3057. Min Act: -0.0000

Data Index: 540419 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2967. Min Act: -0.0001

Data Index: 35 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2413. Min Act: -0.0001

Data Index: 330003 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2791. Min Act: -0.0001

Data Index: 233485 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2854. Min Act: -0.0001

Data Index: 442715 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2727. Min Act: -0.0000

Data Index: 1001054 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2343. Min Act: -0.0001

Data Index: 928492 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1047654 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2712. Min Act: -0.0001

Data Index: 904797 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2806. Min Act: -0.0000

Data Index: 750096 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2608. Min Act: -0.0000

Data Index: 837518 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2581. Min Act: -0.0000

Data Index: 328309 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2318. Min Act: -0.0001

Data Index: 143155 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2419. Min Act: -0.0001

Data Index: 97278 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2183. Min Act: -0.0000

Data Index: 845908 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2342. Min Act: -0.0001

Data Index: 1300609 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1277091 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 0.3611. Min Range: -0.3611

Max Act: 0.2209. Min Act: -0.0000

Data Index: 607856 (C4 (Web Text))

Max Activating Token Index: 282