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

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

Neuron 545 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0460. Min Act: -0.0002

Data Index: 588777 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0437. Min Act: -0.0002

Data Index: 955751 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0389. Min Act: -0.0002

Data Index: 460724 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0379. Min Act: -0.0002

Data Index: 959102 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0374. Min Act: -0.0001

Data Index: 1349029 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0379. Min Act: -0.0001

Data Index: 311435 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0378. Min Act: -0.0002

Data Index: 49882 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0361. Min Act: -0.0002

Data Index: 584487 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0347. Min Act: -0.0001

Data Index: 599400 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0368. Min Act: -0.0002

Data Index: 381071 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0362. Min Act: -0.0002

Data Index: 847044 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0357. Min Act: -0.0002

Data Index: 260365 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0350. Min Act: -0.0001

Data Index: 836477 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0334. Min Act: -0.0002

Data Index: 563633 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0362. Min Act: -0.0002

Data Index: 67502 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0348. Min Act: -0.0002

Data Index: 829742 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0348. Min Act: -0.0002

Data Index: 186125 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0333. Min Act: -0.0002

Data Index: 52857 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0338. Min Act: -0.0001

Data Index: 440554 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0319. Min Act: -0.0001

Data Index: 732960 (C4 (Web Text))

Max Activating Token Index: 447