Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3800 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1304. Min Range: -1.1304

Max Act: 1.0846. Min Act: -0.0000

Data Index: 70291 (The Pile)

Max Activating Token Index: 306

Text #1

Max Range: 1.1304. Min Range: -1.1304

Max Act: 1.1304. Min Act: -0.0000

Data Index: 1936183 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1218320 (The Pile)

Max Activating Token Index: 336

Text #3

Max Range: 1.1304. Min Range: -1.1304

Max Act: 1.0491. Min Act: -0.0000

Data Index: 1818653 (The Pile)

Max Activating Token Index: 321

Text #4

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.9414. Min Act: -0.0000

Data Index: 821655 (The Pile)

Max Activating Token Index: 300

Text #5

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.9760. Min Act: -0.0000

Data Index: 780067 (The Pile)

Max Activating Token Index: 186

Text #6

Max Range: 1.1304. Min Range: -1.1304

Max Act: 1.0146. Min Act: -0.0000

Data Index: 1082778 (The Pile)

Max Activating Token Index: 507

Text #7

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.9656. Min Act: -0.0000

Data Index: 1906957 (The Pile)

Max Activating Token Index: 904

Text #8

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1040002 (The Pile)

Max Activating Token Index: 131

Text #9

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.8449. Min Act: -0.0000

Data Index: 999252 (The Pile)

Max Activating Token Index: 760

Text #10

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.9121. Min Act: -0.0000

Data Index: 158865 (The Pile)

Max Activating Token Index: 952

Text #11

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.8393. Min Act: -0.0000

Data Index: 161947 (The Pile)

Max Activating Token Index: 103

Text #12

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.7817. Min Act: -0.0000

Data Index: 1865152 (The Pile)

Max Activating Token Index: 974

Text #13

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.8135. Min Act: -0.0000

Data Index: 1264394 (The Pile)

Max Activating Token Index: 657

Text #14

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.7830. Min Act: -0.0000

Data Index: 498657 (The Pile)

Max Activating Token Index: 336

Text #15

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1975424 (The Pile)

Max Activating Token Index: 355

Text #16

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1132266 (The Pile)

Max Activating Token Index: 985

Text #17

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.7758. Min Act: -0.0000

Data Index: 832052 (The Pile)

Max Activating Token Index: 834

Text #18

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.7596. Min Act: -0.0000

Data Index: 567929 (The Pile)

Max Activating Token Index: 365

Text #19

Max Range: 1.1304. Min Range: -1.1304

Max Act: 0.7359. Min Act: -0.0000

Data Index: 267936 (The Pile)

Max Activating Token Index: 991