Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 432 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0327. Min Act: -0.0006

Data Index: 963645 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0006

Data Index: 774273 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0006

Data Index: 515003 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0323. Min Act: -0.0006

Data Index: 961661 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0321. Min Act: -0.0006

Data Index: 269239 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0320. Min Act: -0.0005

Data Index: 273065 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0320. Min Act: -0.0005

Data Index: 247067 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0313. Min Act: -0.0005

Data Index: 813177 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0304. Min Act: -0.0006

Data Index: 231180 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0308. Min Act: -0.0006

Data Index: 1119577 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0307. Min Act: -0.0006

Data Index: 82435 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0306. Min Act: -0.0005

Data Index: 1283905 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0306. Min Act: -0.0005

Data Index: 77892 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0312. Min Act: -0.0005

Data Index: 1001204 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0293. Min Act: -0.0006

Data Index: 68952 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0297. Min Act: -0.0005

Data Index: 1284443 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0290. Min Act: -0.0005

Data Index: 325671 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0301. Min Act: -0.0005

Data Index: 98404 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0295. Min Act: -0.0006

Data Index: 1283830 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0292. Min Act: -0.0006

Data Index: 1097434 (C4 (Web Text))

Max Activating Token Index: 286