Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 813 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1182852 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1106910 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0413. Min Act: -0.0002

Data Index: 423639 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0348. Min Act: -0.0002

Data Index: 618423 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1274826 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0371. Min Act: -0.0002

Data Index: 8590 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0334. Min Act: -0.0001

Data Index: 845252 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0346. Min Act: -0.0002

Data Index: 306502 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0346. Min Act: -0.0002

Data Index: 846767 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0335. Min Act: -0.0002

Data Index: 737979 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1249319 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0317. Min Act: -0.0002

Data Index: 684738 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0301. Min Act: -0.0002

Data Index: 814273 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0310. Min Act: -0.0002

Data Index: 667721 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0308. Min Act: -0.0002

Data Index: 743009 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1156467 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0297. Min Act: -0.0001

Data Index: 1136113 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0303. Min Act: -0.0002

Data Index: 838235 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0304. Min Act: -0.0002

Data Index: 493486 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0305. Min Act: -0.0002

Data Index: 241029 (C4 (Web Text))

Max Activating Token Index: 43