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

Dataset: The Pile

Neuron 1178 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: 3.2384. Min Range: -3.2384

Max Act: 3.1134. Min Act: -0.0000

Data Index: 1112734 (The Pile)

Max Activating Token Index: 210

Text #1

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.2384. Min Act: -0.0000

Data Index: 1010088 (The Pile)

Max Activating Token Index: 42

Text #2

Max Range: 3.2384. Min Range: -3.2384

Max Act: 2.7453. Min Act: -0.0000

Data Index: 900094 (The Pile)

Max Activating Token Index: 677

Text #3

Max Range: 3.2384. Min Range: -3.2384

Max Act: 2.3678. Min Act: -0.0000

Data Index: 767502 (The Pile)

Max Activating Token Index: 132

Text #4

Max Range: 3.2384. Min Range: -3.2384

Max Act: 2.9046. Min Act: -0.0000

Data Index: 656677 (The Pile)

Max Activating Token Index: 495

Text #5

Max Range: 3.2384. Min Range: -3.2384

Max Act: 2.5949. Min Act: -0.0000

Data Index: 1136929 (The Pile)

Max Activating Token Index: 94

Text #6

Max Range: 3.2384. Min Range: -3.2384

Max Act: 2.1400. Min Act: -0.0000

Data Index: 1639152 (The Pile)

Max Activating Token Index: 1004

Text #7

Max Range: 3.2384. Min Range: -3.2384

Max Act: 2.1429. Min Act: -0.0000

Data Index: 1589984 (The Pile)

Max Activating Token Index: 928

Text #8

Max Range: 3.2384. Min Range: -3.2384

Max Act: 1.9991. Min Act: -0.0000

Data Index: 962866 (The Pile)

Max Activating Token Index: 218

Text #9

Max Range: 3.2384. Min Range: -3.2384

Max Act: 2.2299. Min Act: -0.0000

Data Index: 1110715 (The Pile)

Max Activating Token Index: 504

Text #10

Max Range: 3.2384. Min Range: -3.2384

Max Act: 2.1129. Min Act: -0.0000

Data Index: 419751 (The Pile)

Max Activating Token Index: 362

Text #11

Max Range: 3.2384. Min Range: -3.2384

Max Act: 2.2768. Min Act: -0.0000

Data Index: 993248 (The Pile)

Max Activating Token Index: 469

Text #12

Max Range: 3.2384. Min Range: -3.2384

Max Act: 2.1324. Min Act: -0.0000

Data Index: 645712 (The Pile)

Max Activating Token Index: 655

Text #13

Max Range: 3.2384. Min Range: -3.2384

Max Act: 2.0536. Min Act: -0.0000

Data Index: 1261634 (The Pile)

Max Activating Token Index: 536

Text #14

Max Range: 3.2384. Min Range: -3.2384

Max Act: 2.2292. Min Act: -0.0000

Data Index: 528845 (The Pile)

Max Activating Token Index: 463

Text #15

Max Range: 3.2384. Min Range: -3.2384

Max Act: 2.6188. Min Act: -0.0000

Data Index: 1014346 (The Pile)

Max Activating Token Index: 938

Text #16

Max Range: 3.2384. Min Range: -3.2384

Max Act: 2.2280. Min Act: -0.0000

Data Index: 735123 (The Pile)

Max Activating Token Index: 736

Text #17

Max Range: 3.2384. Min Range: -3.2384

Max Act: 1.9308. Min Act: 0.0000

Data Index: 1835812 (The Pile)

Max Activating Token Index: 18

Text #18

Max Range: 3.2384. Min Range: -3.2384

Max Act: 2.2443. Min Act: -0.0000

Data Index: 995978 (The Pile)

Max Activating Token Index: 169

Text #19

Max Range: 3.2384. Min Range: -3.2384

Max Act: 2.0130. Min Act: -0.0000

Data Index: 563633 (The Pile)

Max Activating Token Index: 656