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

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

Neuron 4148 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1524767 (Python Code)

Max Activating Token Index: 449

Text #1

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1362532 (Python Code)

Max Activating Token Index: 278

Text #2

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0458. Min Act: -0.0002

Data Index: 345250 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1255291 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0425. Min Act: -0.0002

Data Index: 475125 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0424. Min Act: -0.0002

Data Index: 867431 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0420. Min Act: -0.0002

Data Index: 491410 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0416. Min Act: -0.0002

Data Index: 786331 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0394. Min Act: -0.0002

Data Index: 568205 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0406. Min Act: -0.0002

Data Index: 521836 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0395. Min Act: -0.0002

Data Index: 585228 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1523321 (Python Code)

Max Activating Token Index: 392

Text #12

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0382. Min Act: -0.0002

Data Index: 247776 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0367. Min Act: -0.0002

Data Index: 132270 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0379. Min Act: -0.0002

Data Index: 114352 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0386. Min Act: -0.0002

Data Index: 429717 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0368. Min Act: -0.0002

Data Index: 248119 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0379. Min Act: -0.0002

Data Index: 843888 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0348. Min Act: -0.0002

Data Index: 280489 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0331. Min Act: -0.0002

Data Index: 148578 (C4 (Web Text))

Max Activating Token Index: 348