Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 611 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0135. Min Range: -2.0135

Max Act: 2.0135. Min Act: -0.0000

Data Index: 1033545 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 2.0135. Min Range: -2.0135

Max Act: 1.7013. Min Act: -0.0000

Data Index: 590291 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 2.0135. Min Range: -2.0135

Max Act: 1.7766. Min Act: -0.0000

Data Index: 644692 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 2.0135. Min Range: -2.0135

Max Act: 1.6368. Min Act: -0.0000

Data Index: 1150315 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 2.0135. Min Range: -2.0135

Max Act: 1.6402. Min Act: -0.0000

Data Index: 681995 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 2.0135. Min Range: -2.0135

Max Act: 1.6316. Min Act: -0.0000

Data Index: 1016474 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 2.0135. Min Range: -2.0135

Max Act: 1.5079. Min Act: -0.0000

Data Index: 221181 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 2.0135. Min Range: -2.0135

Max Act: 1.5991. Min Act: -0.0000

Data Index: 271956 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 2.0135. Min Range: -2.0135

Max Act: 1.6929. Min Act: -0.0000

Data Index: 1112022 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 2.0135. Min Range: -2.0135

Max Act: 1.5755. Min Act: -0.0000

Data Index: 687849 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 2.0135. Min Range: -2.0135

Max Act: 1.5012. Min Act: -0.0000

Data Index: 196660 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 2.0135. Min Range: -2.0135

Max Act: 1.5766. Min Act: -0.0000

Data Index: 827587 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 2.0135. Min Range: -2.0135

Max Act: 1.4693. Min Act: -0.0000

Data Index: 962562 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 2.0135. Min Range: -2.0135

Max Act: 1.5290. Min Act: -0.0000

Data Index: 1305007 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 2.0135. Min Range: -2.0135

Max Act: 1.6120. Min Act: -0.0000

Data Index: 301989 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 2.0135. Min Range: -2.0135

Max Act: 1.4293. Min Act: -0.0000

Data Index: 101411 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 2.0135. Min Range: -2.0135

Max Act: 1.5062. Min Act: -0.0000

Data Index: 198931 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 2.0135. Min Range: -2.0135

Max Act: 1.5992. Min Act: -0.0000

Data Index: 1052780 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 2.0135. Min Range: -2.0135

Max Act: 1.4702. Min Act: -0.0000

Data Index: 336196 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 2.0135. Min Range: -2.0135

Max Act: 1.6274. Min Act: -0.0000

Data Index: 304825 (C4 (Web Text))

Max Activating Token Index: 924