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

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

Neuron 4685 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7726. Min Range: -2.7726

Max Act: 2.7726. Min Act: -0.0000

Data Index: 1205400 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 2.7726. Min Range: -2.7726

Max Act: 2.4419. Min Act: -0.0000

Data Index: 572259 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 2.7726. Min Range: -2.7726

Max Act: 2.5093. Min Act: -0.0000

Data Index: 274725 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 2.7726. Min Range: -2.7726

Max Act: 2.3864. Min Act: -0.0000

Data Index: 765135 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 2.7726. Min Range: -2.7726

Max Act: 2.1985. Min Act: -0.0000

Data Index: 857397 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 2.7726. Min Range: -2.7726

Max Act: 2.1424. Min Act: -0.0000

Data Index: 916322 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 2.7726. Min Range: -2.7726

Max Act: 2.1868. Min Act: -0.0000

Data Index: 1186225 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 2.7726. Min Range: -2.7726

Max Act: 2.1858. Min Act: -0.0000

Data Index: 886963 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 2.7726. Min Range: -2.7726

Max Act: 2.1551. Min Act: -0.0000

Data Index: 708115 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 2.7726. Min Range: -2.7726

Max Act: 2.2650. Min Act: -0.0000

Data Index: 87862 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 2.7726. Min Range: -2.7726

Max Act: 2.1386. Min Act: -0.0000

Data Index: 179231 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 2.7726. Min Range: -2.7726

Max Act: 2.1220. Min Act: -0.0000

Data Index: 440199 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 2.7726. Min Range: -2.7726

Max Act: 2.1213. Min Act: -0.0000

Data Index: 19983 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 2.7726. Min Range: -2.7726

Max Act: 2.0967. Min Act: -0.0000

Data Index: 978040 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 2.7726. Min Range: -2.7726

Max Act: 2.0560. Min Act: -0.0000

Data Index: 53272 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 2.7726. Min Range: -2.7726

Max Act: 1.9431. Min Act: -0.0000

Data Index: 905976 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 2.7726. Min Range: -2.7726

Max Act: 2.0361. Min Act: -0.0000

Data Index: 1169191 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 2.7726. Min Range: -2.7726

Max Act: 2.0386. Min Act: -0.0000

Data Index: 880652 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 2.7726. Min Range: -2.7726

Max Act: 2.0196. Min Act: -0.0000

Data Index: 1094150 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 2.7726. Min Range: -2.7726

Max Act: 1.9201. Min Act: -0.0000

Data Index: 869731 (C4 (Web Text))

Max Activating Token Index: 679