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

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

Neuron 4366 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: 1.8321. Min Range: -1.8321

Max Act: 1.8321. Min Act: -0.0001

Data Index: 446895 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.7172. Min Act: -0.0001

Data Index: 325211 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.7007. Min Act: -0.0001

Data Index: 28266 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.4441. Min Act: -0.0001

Data Index: 1295546 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.3908. Min Act: -0.0001

Data Index: 72824 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.3839. Min Act: -0.0001

Data Index: 1137384 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.4197. Min Act: -0.0001

Data Index: 1269857 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.3823. Min Act: -0.0001

Data Index: 697280 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.4047. Min Act: -0.0001

Data Index: 724656 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.3267. Min Act: -0.0001

Data Index: 307963 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.4149. Min Act: -0.0001

Data Index: 134260 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.2104. Min Act: -0.0001

Data Index: 964221 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.3326. Min Act: -0.0001

Data Index: 149095 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.2006. Min Act: -0.0001

Data Index: 29396 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.2805. Min Act: -0.0001

Data Index: 105506 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.2128. Min Act: -0.0001

Data Index: 372602 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.2807. Min Act: -0.0001

Data Index: 375987 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.2286. Min Act: -0.0001

Data Index: 831802 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.2958. Min Act: -0.0001

Data Index: 1150340 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.2147. Min Act: -0.0001

Data Index: 792993 (C4 (Web Text))

Max Activating Token Index: 67