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

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

Neuron 548 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4671. Min Range: -1.4671

Max Act: 1.4671. Min Act: -0.0000

Data Index: 996712 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 1.4671. Min Range: -1.4671

Max Act: 1.4068. Min Act: -0.0001

Data Index: 942153 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 1.4671. Min Range: -1.4671

Max Act: 1.3888. Min Act: -0.0001

Data Index: 740145 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 1.4671. Min Range: -1.4671

Max Act: 1.4279. Min Act: -0.0000

Data Index: 1170097 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 1.4671. Min Range: -1.4671

Max Act: 1.3550. Min Act: -0.0001

Data Index: 1125677 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 1.4671. Min Range: -1.4671

Max Act: 1.3863. Min Act: -0.0001

Data Index: 575261 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 1.4671. Min Range: -1.4671

Max Act: 1.2958. Min Act: -0.0000

Data Index: 542572 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 1.4671. Min Range: -1.4671

Max Act: 1.3730. Min Act: -0.0001

Data Index: 737965 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 1.4671. Min Range: -1.4671

Max Act: 1.3280. Min Act: -0.0001

Data Index: 1148296 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 1.4671. Min Range: -1.4671

Max Act: 1.2852. Min Act: -0.0001

Data Index: 324017 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 1.4671. Min Range: -1.4671

Max Act: 1.3163. Min Act: -0.0000

Data Index: 637910 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 1.4671. Min Range: -1.4671

Max Act: 1.3517. Min Act: -0.0000

Data Index: 442851 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 1.4671. Min Range: -1.4671

Max Act: 1.3290. Min Act: -0.0000

Data Index: 780596 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 1.4671. Min Range: -1.4671

Max Act: 1.2515. Min Act: -0.0000

Data Index: 975590 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 1.4671. Min Range: -1.4671

Max Act: 1.2681. Min Act: -0.0001

Data Index: 1048665 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 1.4671. Min Range: -1.4671

Max Act: 1.2656. Min Act: -0.0001

Data Index: 1269866 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 1.4671. Min Range: -1.4671

Max Act: 1.2169. Min Act: -0.0000

Data Index: 880687 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 1.4671. Min Range: -1.4671

Max Act: 1.2943. Min Act: -0.0001

Data Index: 82100 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 1.4671. Min Range: -1.4671

Max Act: 1.2526. Min Act: -0.0000

Data Index: 1131743 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 1.4671. Min Range: -1.4671

Max Act: 1.2445. Min Act: -0.0001

Data Index: 577677 (C4 (Web Text))

Max Activating Token Index: 20