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

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

Neuron 1702 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0549. Min Act: -0.0000

Data Index: 1476625 (Python Code)

Max Activating Token Index: 663

Text #1

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0415. Min Act: -0.0000

Data Index: 1042879 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0389. Min Act: -0.0000

Data Index: 807378 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0352. Min Act: -0.0000

Data Index: 1549461 (Python Code)

Max Activating Token Index: 372

Text #4

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0343. Min Act: -0.0000

Data Index: 1371765 (Python Code)

Max Activating Token Index: 194

Text #5

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0355. Min Act: -0.0000

Data Index: 1594356 (Python Code)

Max Activating Token Index: 601

Text #6

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0368. Min Act: -0.0000

Data Index: 559779 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0349. Min Act: -0.0000

Data Index: 1626697 (Python Code)

Max Activating Token Index: 808

Text #8

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0330. Min Act: -0.0000

Data Index: 1432282 (Python Code)

Max Activating Token Index: 788

Text #9

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0347. Min Act: -0.0000

Data Index: 1140071 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0371. Min Act: -0.0000

Data Index: 1282919 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0314. Min Act: -0.0000

Data Index: 1021756 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0303. Min Act: -0.0000

Data Index: 188717 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0298. Min Act: -0.0000

Data Index: 88475 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0291. Min Act: -0.0000

Data Index: 718872 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0301. Min Act: -0.0000

Data Index: 1580306 (Python Code)

Max Activating Token Index: 793

Text #16

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0294. Min Act: -0.0000

Data Index: 1454979 (Python Code)

Max Activating Token Index: 568

Text #17

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0288. Min Act: -0.0000

Data Index: 489952 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0280. Min Act: -0.0000

Data Index: 1149352 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0287. Min Act: -0.0000

Data Index: 1602029 (Python Code)

Max Activating Token Index: 184