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

Dataset: The Pile

Neuron 750 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.8342. Min Act: -0.0000

Data Index: 320107 (The Pile)

Max Activating Token Index: 692

Text #1

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.8593. Min Act: -0.0000

Data Index: 753445 (The Pile)

Max Activating Token Index: 250

Text #2

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.8385. Min Act: -0.0000

Data Index: 1936433 (The Pile)

Max Activating Token Index: 301

Text #3

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.7522. Min Act: -0.0000

Data Index: 578459 (The Pile)

Max Activating Token Index: 317

Text #4

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.7373. Min Act: -0.0000

Data Index: 1442653 (The Pile)

Max Activating Token Index: 112

Text #5

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.7474. Min Act: -0.0000

Data Index: 1430675 (The Pile)

Max Activating Token Index: 422

Text #6

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.7226. Min Act: -0.0000

Data Index: 801928 (The Pile)

Max Activating Token Index: 186

Text #7

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6979. Min Act: -0.0000

Data Index: 1238672 (The Pile)

Max Activating Token Index: 322

Text #8

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6726. Min Act: -0.0000

Data Index: 1877979 (The Pile)

Max Activating Token Index: 917

Text #9

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1188327 (The Pile)

Max Activating Token Index: 735

Text #10

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.7116. Min Act: -0.0000

Data Index: 1624263 (The Pile)

Max Activating Token Index: 253

Text #11

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1955514 (The Pile)

Max Activating Token Index: 449

Text #12

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6457. Min Act: -0.0000

Data Index: 310711 (The Pile)

Max Activating Token Index: 20

Text #13

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6281. Min Act: -0.0000

Data Index: 1188429 (The Pile)

Max Activating Token Index: 659

Text #14

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.5848. Min Act: -0.0000

Data Index: 1323913 (The Pile)

Max Activating Token Index: 631

Text #15

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6375. Min Act: -0.0000

Data Index: 26739 (The Pile)

Max Activating Token Index: 581

Text #16

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1237134 (The Pile)

Max Activating Token Index: 1020

Text #17

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6130. Min Act: 0.0000

Data Index: 591271 (The Pile)

Max Activating Token Index: 164

Text #18

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.5443. Min Act: -0.0000

Data Index: 465344 (The Pile)

Max Activating Token Index: 179

Text #19

Max Range: 0.8593. Min Range: -0.8593

Max Act: 0.6034. Min Act: -0.0000

Data Index: 115968 (The Pile)

Max Activating Token Index: 452