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

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

Neuron 2716 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.6069. Min Act: -0.0001

Data Index: 566979 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.4415. Min Act: -0.0001

Data Index: 365605 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.4002. Min Act: -0.0001

Data Index: 780869 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.3369. Min Act: -0.0001

Data Index: 1641897 (Python Code)

Max Activating Token Index: 434

Text #4

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.3713. Min Act: -0.0001

Data Index: 327134 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.3622. Min Act: -0.0001

Data Index: 151934 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.3128. Min Act: -0.0001

Data Index: 292177 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.3069. Min Act: -0.0001

Data Index: 385251 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.3102. Min Act: -0.0001

Data Index: 604887 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.3299. Min Act: -0.0001

Data Index: 648181 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2810. Min Act: -0.0001

Data Index: 583827 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2573. Min Act: -0.0001

Data Index: 1263300 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2951. Min Act: -0.0001

Data Index: 945291 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2619. Min Act: -0.0001

Data Index: 533793 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1944. Min Act: -0.0001

Data Index: 595111 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2147. Min Act: -0.0001

Data Index: 610132 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2596. Min Act: -0.0001

Data Index: 1008908 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2548. Min Act: -0.0001

Data Index: 1017623 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2174. Min Act: -0.0001

Data Index: 1154443 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2192. Min Act: -0.0001

Data Index: 41327 (C4 (Web Text))

Max Activating Token Index: 615