Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2075 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0546. Min Act: -0.0003

Data Index: 1132602 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0458. Min Act: -0.0003

Data Index: 103807 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0447. Min Act: -0.0003

Data Index: 90946 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0375. Min Act: -0.0003

Data Index: 329224 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0374. Min Act: -0.0003

Data Index: 736653 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0389. Min Act: -0.0003

Data Index: 876093 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1170103 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0339. Min Act: -0.0003

Data Index: 50199 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1349802 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0346. Min Act: -0.0003

Data Index: 690410 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0388. Min Act: -0.0003

Data Index: 1268874 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0326. Min Act: -0.0003

Data Index: 94070 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0342. Min Act: -0.0003

Data Index: 566205 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0356. Min Act: -0.0003

Data Index: 770950 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0315. Min Act: -0.0003

Data Index: 658321 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0378. Min Act: -0.0002

Data Index: 958791 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0321. Min Act: -0.0003

Data Index: 221411 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0327. Min Act: -0.0003

Data Index: 1309215 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0310. Min Act: -0.0002

Data Index: 507922 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0315. Min Act: -0.0003

Data Index: 895092 (C4 (Web Text))

Max Activating Token Index: 34