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

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

Neuron 3765 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1199327 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0472. Min Act: -0.0001

Data Index: 726604 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0422. Min Act: -0.0000

Data Index: 761315 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0514. Min Act: -0.0000

Data Index: 1154080 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0417. Min Act: -0.0000

Data Index: 1152572 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0438. Min Act: -0.0000

Data Index: 15085 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0385. Min Act: -0.0001

Data Index: 272625 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0384. Min Act: -0.0000

Data Index: 461506 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0372. Min Act: -0.0001

Data Index: 1345539 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0346. Min Act: -0.0001

Data Index: 1279018 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0319. Min Act: -0.0000

Data Index: 169791 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0322. Min Act: -0.0000

Data Index: 119733 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0313. Min Act: -0.0000

Data Index: 381195 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0301. Min Act: -0.0000

Data Index: 289038 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0330. Min Act: -0.0001

Data Index: 1023231 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0319. Min Act: -0.0000

Data Index: 952598 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1037910 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0321. Min Act: -0.0000

Data Index: 1655733 (Python Code)

Max Activating Token Index: 107

Text #18

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0300. Min Act: -0.0001

Data Index: 237931 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0323. Min Act: -0.0000

Data Index: 487566 (C4 (Web Text))

Max Activating Token Index: 811