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

Dataset: The Pile

Neuron 4769 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.7303. Min Act: 0.0000

Data Index: 290846 (The Pile)

Max Activating Token Index: 334

Text #1

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.3399. Min Act: -0.0000

Data Index: 314553 (The Pile)

Max Activating Token Index: 238

Text #2

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.4099. Min Act: -0.0000

Data Index: 1687675 (The Pile)

Max Activating Token Index: 635

Text #3

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.3085. Min Act: -0.0000

Data Index: 1241249 (The Pile)

Max Activating Token Index: 422

Text #4

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.2219. Min Act: -0.0000

Data Index: 1191610 (The Pile)

Max Activating Token Index: 147

Text #5

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.2863. Min Act: -0.0000

Data Index: 3364 (The Pile)

Max Activating Token Index: 288

Text #6

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.1974. Min Act: -0.0000

Data Index: 446434 (The Pile)

Max Activating Token Index: 290

Text #7

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.2436. Min Act: -0.0000

Data Index: 67720 (The Pile)

Max Activating Token Index: 589

Text #8

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.2036. Min Act: -0.0000

Data Index: 36616 (The Pile)

Max Activating Token Index: 722

Text #9

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.1872. Min Act: -0.0000

Data Index: 1605517 (The Pile)

Max Activating Token Index: 582

Text #10

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.2583. Min Act: -0.0000

Data Index: 1357288 (The Pile)

Max Activating Token Index: 255

Text #11

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.1928. Min Act: -0.0000

Data Index: 1221982 (The Pile)

Max Activating Token Index: 104

Text #12

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.1259. Min Act: -0.0000

Data Index: 193791 (The Pile)

Max Activating Token Index: 567

Text #13

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.1712. Min Act: -0.0000

Data Index: 1577331 (The Pile)

Max Activating Token Index: 682

Text #14

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.1671. Min Act: -0.0000

Data Index: 660040 (The Pile)

Max Activating Token Index: 538

Text #15

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.0990. Min Act: -0.0000

Data Index: 930343 (The Pile)

Max Activating Token Index: 613

Text #16

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.0993. Min Act: -0.0000

Data Index: 886094 (The Pile)

Max Activating Token Index: 946

Text #17

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.2184. Min Act: -0.0000

Data Index: 741272 (The Pile)

Max Activating Token Index: 729

Text #18

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.1155. Min Act: -0.0000

Data Index: 1873182 (The Pile)

Max Activating Token Index: 41

Text #19

Max Range: 1.7303. Min Range: -1.7303

Max Act: 1.1478. Min Act: -0.0000

Data Index: 1522158 (The Pile)

Max Activating Token Index: 474