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

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

Neuron 3156 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5255. Min Range: -7.5255

Max Act: 7.4185. Min Act: -0.0000

Data Index: 739487 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 7.5255. Min Range: -7.5255

Max Act: 7.5255. Min Act: -0.0000

Data Index: 263167 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 7.5255. Min Range: -7.5255

Max Act: 6.9848. Min Act: -0.0000

Data Index: 1163267 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 7.5255. Min Range: -7.5255

Max Act: 6.8881. Min Act: -0.0000

Data Index: 1067234 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 7.5255. Min Range: -7.5255

Max Act: 6.9038. Min Act: -0.0000

Data Index: 1026373 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 7.5255. Min Range: -7.5255

Max Act: 6.6989. Min Act: -0.0001

Data Index: 103030 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 7.5255. Min Range: -7.5255

Max Act: 6.7571. Min Act: -0.0001

Data Index: 81959 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 7.5255. Min Range: -7.5255

Max Act: 6.6570. Min Act: -0.0001

Data Index: 163933 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 7.5255. Min Range: -7.5255

Max Act: 6.8089. Min Act: -0.0001

Data Index: 1098741 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 7.5255. Min Range: -7.5255

Max Act: 6.6251. Min Act: -0.0000

Data Index: 1338209 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 7.5255. Min Range: -7.5255

Max Act: 6.4250. Min Act: -0.0000

Data Index: 1058936 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 7.5255. Min Range: -7.5255

Max Act: 6.5864. Min Act: -0.0000

Data Index: 254430 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 7.5255. Min Range: -7.5255

Max Act: 6.5191. Min Act: -0.0000

Data Index: 956263 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 7.5255. Min Range: -7.5255

Max Act: 6.3097. Min Act: -0.0000

Data Index: 663370 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 7.5255. Min Range: -7.5255

Max Act: 6.4368. Min Act: -0.0000

Data Index: 491539 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 7.5255. Min Range: -7.5255

Max Act: 6.2226. Min Act: -0.0001

Data Index: 800030 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 7.5255. Min Range: -7.5255

Max Act: 6.2335. Min Act: -0.0000

Data Index: 1087906 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 7.5255. Min Range: -7.5255

Max Act: 6.4135. Min Act: -0.0000

Data Index: 921329 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 7.5255. Min Range: -7.5255

Max Act: 6.3849. Min Act: -0.0000

Data Index: 107703 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 7.5255. Min Range: -7.5255

Max Act: 6.0171. Min Act: -0.0000

Data Index: 131140 (C4 (Web Text))

Max Activating Token Index: 865