Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4228 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.3336. Min Act: -0.0000

Data Index: 1602344 (The Pile)

Max Activating Token Index: 364

Text #1

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2919. Min Act: -0.0000

Data Index: 966342 (The Pile)

Max Activating Token Index: 211

Text #2

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2880. Min Act: -0.0000

Data Index: 276651 (The Pile)

Max Activating Token Index: 275

Text #3

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2773. Min Act: -0.0000

Data Index: 1230632 (The Pile)

Max Activating Token Index: 786

Text #4

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2291. Min Act: -0.0000

Data Index: 1734096 (The Pile)

Max Activating Token Index: 650

Text #5

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1217933 (The Pile)

Max Activating Token Index: 328

Text #6

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2446. Min Act: -0.0000

Data Index: 871698 (The Pile)

Max Activating Token Index: 147

Text #7

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2256. Min Act: -0.0000

Data Index: 1817813 (The Pile)

Max Activating Token Index: 482

Text #8

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2326. Min Act: -0.0000

Data Index: 185737 (The Pile)

Max Activating Token Index: 883

Text #9

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1427891 (The Pile)

Max Activating Token Index: 20

Text #10

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2261. Min Act: -0.0000

Data Index: 22262 (The Pile)

Max Activating Token Index: 835

Text #11

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1371981 (The Pile)

Max Activating Token Index: 712

Text #12

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2315. Min Act: -0.0000

Data Index: 1080131 (The Pile)

Max Activating Token Index: 189

Text #13

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2452. Min Act: -0.0000

Data Index: 800312 (The Pile)

Max Activating Token Index: 709

Text #14

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2169. Min Act: -0.0000

Data Index: 83353 (The Pile)

Max Activating Token Index: 165

Text #15

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2273. Min Act: -0.0000

Data Index: 438049 (The Pile)

Max Activating Token Index: 618

Text #16

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1585546 (The Pile)

Max Activating Token Index: 593

Text #17

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2382. Min Act: -0.0000

Data Index: 1559980 (The Pile)

Max Activating Token Index: 147

Text #18

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1724478 (The Pile)

Max Activating Token Index: 899

Text #19

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2533. Min Act: -0.0000

Data Index: 1974544 (The Pile)

Max Activating Token Index: 802