Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2605 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.7199. Min Range: -4.7199

Max Act: 4.4892. Min Act: -0.0000

Data Index: 1327838 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 4.7199. Min Range: -4.7199

Max Act: 4.3991. Min Act: -0.0000

Data Index: 492725 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 4.7199. Min Range: -4.7199

Max Act: 4.7199. Min Act: -0.0000

Data Index: 275454 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 4.7199. Min Range: -4.7199

Max Act: 4.4130. Min Act: -0.0000

Data Index: 35140 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 4.7199. Min Range: -4.7199

Max Act: 4.3467. Min Act: -0.0000

Data Index: 243237 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 4.7199. Min Range: -4.7199

Max Act: 4.0011. Min Act: -0.0000

Data Index: 1304631 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 4.7199. Min Range: -4.7199

Max Act: 3.9701. Min Act: -0.0000

Data Index: 1345818 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 4.7199. Min Range: -4.7199

Max Act: 3.9726. Min Act: -0.0000

Data Index: 155411 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 4.7199. Min Range: -4.7199

Max Act: 3.9611. Min Act: -0.0000

Data Index: 1082992 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 4.7199. Min Range: -4.7199

Max Act: 4.1012. Min Act: -0.0000

Data Index: 668274 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 4.7199. Min Range: -4.7199

Max Act: 3.8784. Min Act: -0.0000

Data Index: 860913 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 4.7199. Min Range: -4.7199

Max Act: 3.8204. Min Act: -0.0000

Data Index: 886821 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 4.7199. Min Range: -4.7199

Max Act: 3.8266. Min Act: -0.0000

Data Index: 468938 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 4.7199. Min Range: -4.7199

Max Act: 3.6889. Min Act: -0.0000

Data Index: 258167 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 4.7199. Min Range: -4.7199

Max Act: 3.7722. Min Act: -0.0000

Data Index: 886059 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 4.7199. Min Range: -4.7199

Max Act: 3.3408. Min Act: -0.0000

Data Index: 878964 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 4.7199. Min Range: -4.7199

Max Act: 3.3843. Min Act: -0.0000

Data Index: 1248780 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 4.7199. Min Range: -4.7199

Max Act: 3.0935. Min Act: -0.0000

Data Index: 1319213 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 4.7199. Min Range: -4.7199

Max Act: 3.0488. Min Act: -0.0000

Data Index: 541590 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 4.7199. Min Range: -4.7199

Max Act: 3.3288. Min Act: -0.0000

Data Index: 96742 (C4 (Web Text))

Max Activating Token Index: 130