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

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

Neuron 79 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6607. Min Range: -5.6607

Max Act: 5.6607. Min Act: -0.0001

Data Index: 887641 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 5.6607. Min Range: -5.6607

Max Act: 4.8497. Min Act: -0.0001

Data Index: 636490 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 5.6607. Min Range: -5.6607

Max Act: 3.9617. Min Act: -0.0001

Data Index: 778945 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 5.6607. Min Range: -5.6607

Max Act: 4.0531. Min Act: -0.0001

Data Index: 1078630 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 5.6607. Min Range: -5.6607

Max Act: 3.8345. Min Act: -0.0001

Data Index: 624417 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 5.6607. Min Range: -5.6607

Max Act: 3.6429. Min Act: -0.0001

Data Index: 572191 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 5.6607. Min Range: -5.6607

Max Act: 3.6719. Min Act: -0.0001

Data Index: 676662 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 5.6607. Min Range: -5.6607

Max Act: 3.6578. Min Act: -0.0001

Data Index: 1087749 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 5.6607. Min Range: -5.6607

Max Act: 3.6136. Min Act: -0.0001

Data Index: 389670 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 5.6607. Min Range: -5.6607

Max Act: 3.7690. Min Act: -0.0001

Data Index: 527350 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 5.6607. Min Range: -5.6607

Max Act: 3.6085. Min Act: -0.0001

Data Index: 336104 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 5.6607. Min Range: -5.6607

Max Act: 3.2438. Min Act: -0.0001

Data Index: 559419 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 5.6607. Min Range: -5.6607

Max Act: 3.5127. Min Act: -0.0001

Data Index: 205982 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 5.6607. Min Range: -5.6607

Max Act: 3.3126. Min Act: -0.0001

Data Index: 456180 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 5.6607. Min Range: -5.6607

Max Act: 3.3388. Min Act: -0.0001

Data Index: 1296259 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 5.6607. Min Range: -5.6607

Max Act: 3.4788. Min Act: -0.0001

Data Index: 798021 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 5.6607. Min Range: -5.6607

Max Act: 3.3155. Min Act: -0.0001

Data Index: 1201178 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 5.6607. Min Range: -5.6607

Max Act: 3.4597. Min Act: -0.0001

Data Index: 850772 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 5.6607. Min Range: -5.6607

Max Act: 3.4413. Min Act: -0.0001

Data Index: 1173495 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 5.6607. Min Range: -5.6607

Max Act: 3.3915. Min Act: -0.0001

Data Index: 180089 (C4 (Web Text))

Max Activating Token Index: 1013