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

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

Neuron 3879 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0383. Min Range: -1.0383

Max Act: 1.0022. Min Act: -0.0003

Data Index: 44210 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 1.0383. Min Range: -1.0383

Max Act: 1.0383. Min Act: -0.0003

Data Index: 306689 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9099. Min Act: -0.0003

Data Index: 912497 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9261. Min Act: -0.0003

Data Index: 130618 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9586. Min Act: -0.0003

Data Index: 1048704 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9193. Min Act: -0.0003

Data Index: 591946 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9480. Min Act: -0.0003

Data Index: 238867 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9158. Min Act: -0.0003

Data Index: 1127667 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9202. Min Act: -0.0003

Data Index: 1018859 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8938. Min Act: -0.0003

Data Index: 262363 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8877. Min Act: -0.0003

Data Index: 929274 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9093. Min Act: -0.0003

Data Index: 965728 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8585. Min Act: -0.0003

Data Index: 1118764 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8803. Min Act: -0.0003

Data Index: 331124 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.7498. Min Act: -0.0003

Data Index: 185441 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8187. Min Act: -0.0003

Data Index: 778182 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8991. Min Act: -0.0003

Data Index: 702191 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8186. Min Act: -0.0003

Data Index: 814952 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8204. Min Act: -0.0003

Data Index: 267887 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8175. Min Act: -0.0003

Data Index: 629506 (C4 (Web Text))

Max Activating Token Index: 607