Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3735 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.1410. Min Act: -0.0001

Data Index: 1320516 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.2029. Min Act: -0.0001

Data Index: 945802 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.1183. Min Act: -0.0001

Data Index: 396174 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.0514. Min Act: -0.0001

Data Index: 417838 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.0791. Min Act: -0.0001

Data Index: 424946 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9938. Min Act: -0.0001

Data Index: 1185373 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.0339. Min Act: -0.0001

Data Index: 400077 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.0218. Min Act: -0.0001

Data Index: 1109475 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.0054. Min Act: -0.0001

Data Index: 1338176 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9769. Min Act: -0.0001

Data Index: 840638 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9942. Min Act: -0.0001

Data Index: 338238 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9928. Min Act: -0.0001

Data Index: 497190 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.0622. Min Act: -0.0001

Data Index: 137375 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9855. Min Act: -0.0001

Data Index: 1177999 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9353. Min Act: -0.0001

Data Index: 1031396 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.0139. Min Act: -0.0001

Data Index: 876835 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9455. Min Act: -0.0001

Data Index: 182327 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9751. Min Act: -0.0001

Data Index: 422741 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9835. Min Act: -0.0001

Data Index: 463670 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8670. Min Act: -0.0001

Data Index: 1152243 (C4 (Web Text))

Max Activating Token Index: 467