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

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

Neuron 670 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0408. Min Act: -0.0001

Data Index: 695437 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0354. Min Act: -0.0001

Data Index: 1151522 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0366. Min Act: -0.0001

Data Index: 345689 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0364. Min Act: -0.0001

Data Index: 578871 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0356. Min Act: -0.0001

Data Index: 582568 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0361. Min Act: -0.0001

Data Index: 263596 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0342. Min Act: -0.0001

Data Index: 1286206 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1232992 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0338. Min Act: -0.0001

Data Index: 1338389 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0325. Min Act: -0.0001

Data Index: 191312 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0353. Min Act: -0.0001

Data Index: 251866 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0352. Min Act: -0.0001

Data Index: 159347 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0329. Min Act: -0.0001

Data Index: 1237899 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0344. Min Act: -0.0001

Data Index: 505474 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0331. Min Act: -0.0001

Data Index: 869661 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0338. Min Act: -0.0001

Data Index: 96821 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0347. Min Act: -0.0001

Data Index: 706857 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0314. Min Act: -0.0001

Data Index: 1301855 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0341. Min Act: -0.0001

Data Index: 1192713 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0314. Min Act: -0.0001

Data Index: 492670 (C4 (Web Text))

Max Activating Token Index: 967