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

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

Neuron 1932 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4702. Min Range: -0.4702

Max Act: 0.4702. Min Act: -0.0001

Data Index: 263549 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.4702. Min Range: -0.4702

Max Act: 0.4216. Min Act: -0.0001

Data Index: 1012433 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.4702. Min Range: -0.4702

Max Act: 0.4038. Min Act: -0.0001

Data Index: 34253 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.4702. Min Range: -0.4702

Max Act: 0.3911. Min Act: -0.0001

Data Index: 1152499 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 0.4702. Min Range: -0.4702

Max Act: 0.4165. Min Act: -0.0001

Data Index: 250089 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.4702. Min Range: -0.4702

Max Act: 0.4080. Min Act: -0.0001

Data Index: 822157 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 0.4702. Min Range: -0.4702

Max Act: 0.3758. Min Act: -0.0001

Data Index: 671946 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 0.4702. Min Range: -0.4702

Max Act: 0.3809. Min Act: -0.0001

Data Index: 3175 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 0.4702. Min Range: -0.4702

Max Act: 0.3467. Min Act: -0.0001

Data Index: 1142611 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.4702. Min Range: -0.4702

Max Act: 0.3483. Min Act: -0.0001

Data Index: 117106 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.4702. Min Range: -0.4702

Max Act: 0.3605. Min Act: -0.0001

Data Index: 386384 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.4702. Min Range: -0.4702

Max Act: 0.3559. Min Act: -0.0001

Data Index: 4040 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.4702. Min Range: -0.4702

Max Act: 0.3647. Min Act: -0.0001

Data Index: 279995 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.4702. Min Range: -0.4702

Max Act: 0.3416. Min Act: -0.0001

Data Index: 1049025 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.4702. Min Range: -0.4702

Max Act: 0.3202. Min Act: -0.0001

Data Index: 421503 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.4702. Min Range: -0.4702

Max Act: 0.3432. Min Act: -0.0001

Data Index: 1173351 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.4702. Min Range: -0.4702

Max Act: 0.3254. Min Act: -0.0001

Data Index: 1085026 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.4702. Min Range: -0.4702

Max Act: 0.3236. Min Act: -0.0001

Data Index: 825871 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.4702. Min Range: -0.4702

Max Act: 0.3320. Min Act: -0.0001

Data Index: 120810 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 0.4702. Min Range: -0.4702

Max Act: 0.3166. Min Act: -0.0001

Data Index: 1038525 (C4 (Web Text))

Max Activating Token Index: 239