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

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

Neuron 2635 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1550. Min Range: -1.1550

Max Act: 1.1550. Min Act: -0.0000

Data Index: 1086294 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 1.1550. Min Range: -1.1550

Max Act: 1.0446. Min Act: -0.0000

Data Index: 907453 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.8138. Min Act: -0.0000

Data Index: 17246 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.7241. Min Act: -0.0000

Data Index: 1354456 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.7177. Min Act: -0.0000

Data Index: 547208 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.6355. Min Act: -0.0000

Data Index: 540068 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.6393. Min Act: -0.0000

Data Index: 782861 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.5769. Min Act: -0.0000

Data Index: 220167 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.6046. Min Act: -0.0000

Data Index: 663997 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.5304. Min Act: -0.0000

Data Index: 506023 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.4848. Min Act: -0.0000

Data Index: 796849 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.5070. Min Act: -0.0000

Data Index: 730500 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.4671. Min Act: -0.0000

Data Index: 651369 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.3919. Min Act: -0.0000

Data Index: 577217 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.4331. Min Act: -0.0000

Data Index: 774227 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.4169. Min Act: -0.0000

Data Index: 1506008 (Python Code)

Max Activating Token Index: 104

Text #16

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.4106. Min Act: -0.0000

Data Index: 1537713 (Python Code)

Max Activating Token Index: 986

Text #17

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1544710 (Python Code)

Max Activating Token Index: 617

Text #18

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.4154. Min Act: -0.0000

Data Index: 918548 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 1.1550. Min Range: -1.1550

Max Act: 0.4189. Min Act: -0.0000

Data Index: 926825 (C4 (Web Text))

Max Activating Token Index: 679