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

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

Neuron 1078 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.5962. Min Act: -0.0000

Data Index: 70082 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.1927. Min Act: -0.0000

Data Index: 38618 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.1033. Min Act: -0.0000

Data Index: 748338 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.1405. Min Act: -0.0000

Data Index: 236551 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 1.5962. Min Range: -1.5962

Max Act: 0.9705. Min Act: -0.0000

Data Index: 1072157 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.0531. Min Act: -0.0000

Data Index: 105359 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.0699. Min Act: -0.0000

Data Index: 358457 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.0738. Min Act: -0.0000

Data Index: 529196 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 1.5962. Min Range: -1.5962

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1350084 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.0188. Min Act: -0.0000

Data Index: 212270 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 1.5962. Min Range: -1.5962

Max Act: 0.9241. Min Act: -0.0000

Data Index: 939731 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 1.5962. Min Range: -1.5962

Max Act: 0.8981. Min Act: -0.0000

Data Index: 1176381 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 1.5962. Min Range: -1.5962

Max Act: 0.8944. Min Act: -0.0000

Data Index: 471091 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 1.5962. Min Range: -1.5962

Max Act: 0.8204. Min Act: -0.0000

Data Index: 648392 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 1.5962. Min Range: -1.5962

Max Act: 0.8486. Min Act: -0.0000

Data Index: 1083120 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 1.5962. Min Range: -1.5962

Max Act: 0.8603. Min Act: -0.0000

Data Index: 319707 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 1.5962. Min Range: -1.5962

Max Act: 0.8098. Min Act: -0.0000

Data Index: 682455 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 1.5962. Min Range: -1.5962

Max Act: 0.9130. Min Act: -0.0000

Data Index: 491240 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 1.5962. Min Range: -1.5962

Max Act: 0.9402. Min Act: -0.0000

Data Index: 30341 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 1.5962. Min Range: -1.5962

Max Act: 0.8447. Min Act: -0.0000

Data Index: 88138 (C4 (Web Text))

Max Activating Token Index: 60