Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1646 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2977. Min Range: -0.2977

Max Act: 0.2977. Min Act: -0.0001

Data Index: 849570 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.2977. Min Range: -0.2977

Max Act: 0.2572. Min Act: -0.0001

Data Index: 530787 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.2977. Min Range: -0.2977

Max Act: 0.2538. Min Act: -0.0001

Data Index: 964712 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.2977. Min Range: -0.2977

Max Act: 0.2405. Min Act: -0.0001

Data Index: 127583 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.2977. Min Range: -0.2977

Max Act: 0.2403. Min Act: -0.0001

Data Index: 337035 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.2977. Min Range: -0.2977

Max Act: 0.2389. Min Act: -0.0001

Data Index: 1110743 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.2977. Min Range: -0.2977

Max Act: 0.2368. Min Act: -0.0001

Data Index: 28404 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.2977. Min Range: -0.2977

Max Act: 0.2222. Min Act: -0.0001

Data Index: 417530 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.2977. Min Range: -0.2977

Max Act: 0.2264. Min Act: -0.0001

Data Index: 736568 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.2977. Min Range: -0.2977

Max Act: 0.2035. Min Act: -0.0001

Data Index: 442485 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.2977. Min Range: -0.2977

Max Act: 0.2188. Min Act: -0.0001

Data Index: 12095 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.2977. Min Range: -0.2977

Max Act: 0.2244. Min Act: -0.0001

Data Index: 1213003 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.2977. Min Range: -0.2977

Max Act: 0.2160. Min Act: -0.0001

Data Index: 1288067 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.2977. Min Range: -0.2977

Max Act: 0.2238. Min Act: -0.0001

Data Index: 746567 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 0.2977. Min Range: -0.2977

Max Act: 0.2203. Min Act: -0.0001

Data Index: 158181 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.2977. Min Range: -0.2977

Max Act: 0.2161. Min Act: -0.0001

Data Index: 388285 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.2977. Min Range: -0.2977

Max Act: 0.2081. Min Act: -0.0001

Data Index: 1218767 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.2977. Min Range: -0.2977

Max Act: 0.2206. Min Act: -0.0001

Data Index: 281653 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 0.2977. Min Range: -0.2977

Max Act: 0.2198. Min Act: -0.0001

Data Index: 764109 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.2977. Min Range: -0.2977

Max Act: 0.2190. Min Act: -0.0001

Data Index: 158141 (C4 (Web Text))

Max Activating Token Index: 586