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

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

Neuron 2696 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2140. Min Range: -1.2140

Max Act: 1.2058. Min Act: -0.0002

Data Index: 32400 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 1.2140. Min Range: -1.2140

Max Act: 1.0583. Min Act: -0.0002

Data Index: 1148415 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 1.2140. Min Range: -1.2140

Max Act: 1.2140. Min Act: -0.0002

Data Index: 680114 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 1.2140. Min Range: -1.2140

Max Act: 1.0571. Min Act: -0.0002

Data Index: 835475 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 1.2140. Min Range: -1.2140

Max Act: 1.1762. Min Act: -0.0002

Data Index: 98984 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 1.2140. Min Range: -1.2140

Max Act: 1.1962. Min Act: -0.0002

Data Index: 528941 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 1.2140. Min Range: -1.2140

Max Act: 1.0649. Min Act: -0.0002

Data Index: 364225 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.9088. Min Act: -0.0002

Data Index: 700195 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.8352. Min Act: -0.0002

Data Index: 627469 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.8831. Min Act: -0.0002

Data Index: 1258000 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.9365. Min Act: -0.0002

Data Index: 1172121 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.9169. Min Act: -0.0002

Data Index: 695822 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.9260. Min Act: -0.0002

Data Index: 1039269 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 1.2140. Min Range: -1.2140

Max Act: 1.0620. Min Act: -0.0002

Data Index: 63788 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.9936. Min Act: -0.0002

Data Index: 1028331 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.9337. Min Act: -0.0002

Data Index: 559081 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.9995. Min Act: -0.0002

Data Index: 1294429 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.8885. Min Act: -0.0002

Data Index: 1194498 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.9374. Min Act: -0.0002

Data Index: 908689 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 1.2140. Min Range: -1.2140

Max Act: 0.8533. Min Act: -0.0002

Data Index: 287737 (C4 (Web Text))

Max Activating Token Index: 1021