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

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

Neuron 202 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7360. Min Act: -0.0002

Data Index: 482264 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7914. Min Act: -0.0002

Data Index: 217711 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6371. Min Act: -0.0002

Data Index: 893535 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.5912. Min Act: -0.0002

Data Index: 971399 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6667. Min Act: -0.0002

Data Index: 353159 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.8054. Min Act: -0.0002

Data Index: 352193 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7525. Min Act: -0.0002

Data Index: 1198982 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6656. Min Act: -0.0002

Data Index: 321540 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6834. Min Act: -0.0002

Data Index: 1078993 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6365. Min Act: -0.0002

Data Index: 1091129 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6768. Min Act: -0.0002

Data Index: 111218 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6391. Min Act: -0.0002

Data Index: 888444 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6850. Min Act: -0.0002

Data Index: 913439 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6547. Min Act: -0.0002

Data Index: 603029 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6491. Min Act: -0.0002

Data Index: 1049366 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6866. Min Act: -0.0002

Data Index: 567488 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7026. Min Act: -0.0002

Data Index: 396959 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6491. Min Act: -0.0002

Data Index: 1307226 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6956. Min Act: -0.0002

Data Index: 1214033 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6500. Min Act: -0.0002

Data Index: 308761 (C4 (Web Text))

Max Activating Token Index: 350