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

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

Neuron 3018 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0489. Min Act: -0.0000

Data Index: 909265 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0409. Min Act: -0.0000

Data Index: 1513707 (Python Code)

Max Activating Token Index: 582

Text #2

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0392. Min Act: -0.0000

Data Index: 1102313 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0370. Min Act: -0.0000

Data Index: 427291 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0381. Min Act: -0.0000

Data Index: 1255965 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0387. Min Act: -0.0001

Data Index: 1434139 (Python Code)

Max Activating Token Index: 296

Text #6

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0361. Min Act: -0.0001

Data Index: 628651 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0370. Min Act: -0.0000

Data Index: 1469939 (Python Code)

Max Activating Token Index: 988

Text #8

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0367. Min Act: -0.0000

Data Index: 877735 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0348. Min Act: -0.0000

Data Index: 619159 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0363. Min Act: -0.0000

Data Index: 961352 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0373. Min Act: -0.0000

Data Index: 751260 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0340. Min Act: -0.0000

Data Index: 331424 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0352. Min Act: -0.0000

Data Index: 556427 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0364. Min Act: -0.0000

Data Index: 1155279 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0347. Min Act: -0.0000

Data Index: 1204104 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0343. Min Act: -0.0000

Data Index: 584871 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0344. Min Act: -0.0001

Data Index: 1511586 (Python Code)

Max Activating Token Index: 656

Text #18

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0342. Min Act: -0.0001

Data Index: 1600168 (Python Code)

Max Activating Token Index: 791

Text #19

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0330. Min Act: -0.0000

Data Index: 1047765 (C4 (Web Text))

Max Activating Token Index: 714