Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0435. Min Act: -0.0003

Data Index: 120411 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0405. Min Act: -0.0003

Data Index: 57784 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0412. Min Act: -0.0003

Data Index: 533446 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0374. Min Act: -0.0003

Data Index: 741058 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1159306 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0359. Min Act: -0.0003

Data Index: 415952 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0351. Min Act: -0.0003

Data Index: 802664 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0351. Min Act: -0.0003

Data Index: 221476 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0358. Min Act: -0.0003

Data Index: 165767 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0324. Min Act: -0.0003

Data Index: 4407 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1205538 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0359. Min Act: -0.0003

Data Index: 999193 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0357. Min Act: -0.0003

Data Index: 500676 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0346. Min Act: -0.0003

Data Index: 130034 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0329. Min Act: -0.0003

Data Index: 886064 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0317. Min Act: -0.0003

Data Index: 10245 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0328. Min Act: -0.0003

Data Index: 841789 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0296. Min Act: -0.0003

Data Index: 659031 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1269946 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1325332 (C4 (Web Text))

Max Activating Token Index: 428