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

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

Neuron 1087 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0288. Min Range: -1.0288

Max Act: 1.0288. Min Act: -0.0000

Data Index: 1354299 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.9777. Min Act: -0.0000

Data Index: 491196 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 1.0288. Min Range: -1.0288

Max Act: 1.0150. Min Act: -0.0000

Data Index: 114934 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 1.0288. Min Range: -1.0288

Max Act: 1.0163. Min Act: -0.0000

Data Index: 1283624 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.9329. Min Act: -0.0000

Data Index: 413036 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.9714. Min Act: -0.0000

Data Index: 714727 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.9085. Min Act: -0.0000

Data Index: 54813 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.9111. Min Act: -0.0000

Data Index: 564090 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.9433. Min Act: -0.0000

Data Index: 52223 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.9355. Min Act: -0.0000

Data Index: 1088654 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.9280. Min Act: -0.0000

Data Index: 1065546 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8529. Min Act: -0.0000

Data Index: 1276630 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8845. Min Act: -0.0000

Data Index: 22686 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8894. Min Act: -0.0000

Data Index: 1211274 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8852. Min Act: -0.0000

Data Index: 690485 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8489. Min Act: -0.0000

Data Index: 369054 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8753. Min Act: -0.0000

Data Index: 577296 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8634. Min Act: -0.0000

Data Index: 369393 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8565. Min Act: -0.0000

Data Index: 218087 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8474. Min Act: -0.0000

Data Index: 168314 (C4 (Web Text))

Max Activating Token Index: 476