Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1408 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0593. Min Act: -0.0002

Data Index: 899599 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0473. Min Act: -0.0002

Data Index: 139894 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0388. Min Act: -0.0002

Data Index: 767522 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1240672 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0335. Min Act: -0.0002

Data Index: 617283 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0342. Min Act: -0.0002

Data Index: 787505 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0336. Min Act: -0.0002

Data Index: 756119 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1050053 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0318. Min Act: -0.0002

Data Index: 148125 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0310. Min Act: -0.0002

Data Index: 979375 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0306. Min Act: -0.0002

Data Index: 864412 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0291. Min Act: -0.0002

Data Index: 978713 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1305748 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0304. Min Act: -0.0002

Data Index: 949576 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0300. Min Act: -0.0002

Data Index: 449947 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0290. Min Act: -0.0002

Data Index: 296062 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1166678 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0292. Min Act: -0.0002

Data Index: 457576 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0295. Min Act: -0.0002

Data Index: 17943 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0301. Min Act: -0.0002

Data Index: 332265 (C4 (Web Text))

Max Activating Token Index: 640