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

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

Neuron 305 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.7781. Min Act: -0.0001

Data Index: 1056355 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.7965. Min Act: -0.0001

Data Index: 1354907 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.7034. Min Act: -0.0001

Data Index: 456187 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.7237. Min Act: -0.0001

Data Index: 606006 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.7390. Min Act: -0.0001

Data Index: 132752 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.7093. Min Act: -0.0001

Data Index: 129669 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.7190. Min Act: -0.0001

Data Index: 4405 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6973. Min Act: -0.0001

Data Index: 450894 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6974. Min Act: -0.0001

Data Index: 66570 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6940. Min Act: -0.0001

Data Index: 18933 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6808. Min Act: -0.0001

Data Index: 1020117 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6794. Min Act: -0.0001

Data Index: 335988 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6728. Min Act: -0.0001

Data Index: 333786 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6504. Min Act: -0.0001

Data Index: 496520 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6765. Min Act: -0.0001

Data Index: 1058295 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6642. Min Act: -0.0001

Data Index: 558692 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6625. Min Act: -0.0001

Data Index: 504979 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6599. Min Act: -0.0001

Data Index: 1245682 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6593. Min Act: -0.0001

Data Index: 487288 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6334. Min Act: -0.0001

Data Index: 295250 (C4 (Web Text))

Max Activating Token Index: 74