Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2047 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1290. Min Act: -0.0002

Data Index: 438639 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1053. Min Act: -0.0001

Data Index: 516172 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1095. Min Act: -0.0002

Data Index: 447948 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1067. Min Act: -0.0001

Data Index: 563634 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1045. Min Act: -0.0001

Data Index: 526602 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1004. Min Act: -0.0002

Data Index: 324822 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1006. Min Act: -0.0001

Data Index: 302426 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0993. Min Act: -0.0002

Data Index: 739514 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0953. Min Act: -0.0001

Data Index: 419980 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1234242 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1075. Min Act: -0.0002

Data Index: 999253 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0973. Min Act: -0.0001

Data Index: 234780 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0957. Min Act: -0.0002

Data Index: 506358 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0950. Min Act: -0.0002

Data Index: 367516 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0912. Min Act: -0.0001

Data Index: 177001 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0946. Min Act: -0.0002

Data Index: 826675 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0963. Min Act: -0.0002

Data Index: 261938 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0952. Min Act: -0.0002

Data Index: 894382 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0885. Min Act: -0.0002

Data Index: 594778 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0854. Min Act: -0.0002

Data Index: 639406 (C4 (Web Text))

Max Activating Token Index: 629