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

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

Neuron 2330 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.9340. Min Act: -0.0001

Data Index: 973102 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.8922. Min Act: -0.0001

Data Index: 1062193 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.8921. Min Act: -0.0001

Data Index: 801663 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.9084. Min Act: -0.0001

Data Index: 1070184 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 3.0205. Min Range: -3.0205

Max Act: 3.0205. Min Act: -0.0001

Data Index: 1092939 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.8753. Min Act: -0.0001

Data Index: 810501 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.8580. Min Act: -0.0001

Data Index: 966573 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.8709. Min Act: -0.0001

Data Index: 868624 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.6416. Min Act: -0.0001

Data Index: 909443 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.7810. Min Act: -0.0001

Data Index: 1187817 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.7656. Min Act: -0.0001

Data Index: 509253 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.6357. Min Act: -0.0001

Data Index: 131837 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.7620. Min Act: -0.0001

Data Index: 778332 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.6101. Min Act: -0.0001

Data Index: 1108476 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.8742. Min Act: -0.0001

Data Index: 315238 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.7514. Min Act: -0.0001

Data Index: 742233 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.6240. Min Act: -0.0001

Data Index: 652171 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.7356. Min Act: -0.0001

Data Index: 201736 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.6819. Min Act: -0.0001

Data Index: 645446 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.5461. Min Act: -0.0001

Data Index: 1318366 (C4 (Web Text))

Max Activating Token Index: 526