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

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

Neuron 49 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4108. Min Range: -1.4108

Max Act: 1.4108. Min Act: -0.0001

Data Index: 477334 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 1.4108. Min Range: -1.4108

Max Act: 1.2150. Min Act: -0.0001

Data Index: 1121185 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 1.4108. Min Range: -1.4108

Max Act: 1.2529. Min Act: -0.0001

Data Index: 787843 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 1.4108. Min Range: -1.4108

Max Act: 1.1849. Min Act: -0.0001

Data Index: 624349 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 1.4108. Min Range: -1.4108

Max Act: 1.1532. Min Act: -0.0001

Data Index: 1046988 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 1.4108. Min Range: -1.4108

Max Act: 1.1818. Min Act: -0.0001

Data Index: 978454 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 1.4108. Min Range: -1.4108

Max Act: 1.0319. Min Act: -0.0001

Data Index: 852121 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 1.4108. Min Range: -1.4108

Max Act: 1.0538. Min Act: -0.0001

Data Index: 1127119 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 1.4108. Min Range: -1.4108

Max Act: 1.0769. Min Act: -0.0001

Data Index: 552769 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 1.4108. Min Range: -1.4108

Max Act: 1.0956. Min Act: -0.0001

Data Index: 793849 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.4108. Min Range: -1.4108

Max Act: 0.9941. Min Act: -0.0001

Data Index: 1300578 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 1.4108. Min Range: -1.4108

Max Act: 0.7785. Min Act: -0.0001

Data Index: 1194114 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 1.4108. Min Range: -1.4108

Max Act: 0.9327. Min Act: -0.0001

Data Index: 1055662 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 1.4108. Min Range: -1.4108

Max Act: 0.8180. Min Act: -0.0001

Data Index: 783602 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 1.4108. Min Range: -1.4108

Max Act: 0.7858. Min Act: -0.0001

Data Index: 1220826 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 1.4108. Min Range: -1.4108

Max Act: 0.8107. Min Act: -0.0001

Data Index: 606380 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 1.4108. Min Range: -1.4108

Max Act: 0.8351. Min Act: -0.0001

Data Index: 870292 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 1.4108. Min Range: -1.4108

Max Act: 0.7976. Min Act: -0.0001

Data Index: 1341621 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 1.4108. Min Range: -1.4108

Max Act: 0.7478. Min Act: -0.0001

Data Index: 521475 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 1.4108. Min Range: -1.4108

Max Act: 0.7240. Min Act: -0.0001

Data Index: 519407 (C4 (Web Text))

Max Activating Token Index: 56