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

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

Neuron 26 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0444. Min Act: -0.0006

Data Index: 1270851 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0379. Min Act: -0.0006

Data Index: 761467 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0363. Min Act: -0.0006

Data Index: 519777 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0364. Min Act: -0.0006

Data Index: 934505 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0386. Min Act: -0.0006

Data Index: 1213742 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0347. Min Act: -0.0006

Data Index: 737673 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0355. Min Act: -0.0006

Data Index: 322381 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0351. Min Act: -0.0006

Data Index: 326785 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0361. Min Act: -0.0006

Data Index: 539747 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0367. Min Act: -0.0006

Data Index: 273098 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0316. Min Act: -0.0006

Data Index: 1085401 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0335. Min Act: -0.0006

Data Index: 1293081 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0312. Min Act: -0.0006

Data Index: 573811 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0336. Min Act: -0.0006

Data Index: 116501 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0337. Min Act: -0.0006

Data Index: 546351 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0323. Min Act: -0.0006

Data Index: 1280248 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0295. Min Act: -0.0006

Data Index: 407727 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0333. Min Act: -0.0006

Data Index: 761328 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0318. Min Act: -0.0006

Data Index: 1252053 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0333. Min Act: -0.0006

Data Index: 485812 (C4 (Web Text))

Max Activating Token Index: 440