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

Dataset: The Pile

Neuron 3452 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1736962 (The Pile)

Max Activating Token Index: 698

Text #1

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1715251 (The Pile)

Max Activating Token Index: 863

Text #2

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2974. Min Act: -0.0000

Data Index: 161660 (The Pile)

Max Activating Token Index: 161

Text #3

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1383794 (The Pile)

Max Activating Token Index: 175

Text #4

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1281151 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1260198 (The Pile)

Max Activating Token Index: 275

Text #6

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1263302 (The Pile)

Max Activating Token Index: 263

Text #7

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2492. Min Act: -0.0000

Data Index: 1172649 (The Pile)

Max Activating Token Index: 438

Text #8

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2411. Min Act: -0.0000

Data Index: 665995 (The Pile)

Max Activating Token Index: 683

Text #9

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1748670 (The Pile)

Max Activating Token Index: 342

Text #10

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2351. Min Act: -0.0000

Data Index: 1213745 (The Pile)

Max Activating Token Index: 515

Text #11

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2408. Min Act: -0.0000

Data Index: 11647 (The Pile)

Max Activating Token Index: 729

Text #12

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2286. Min Act: -0.0000

Data Index: 421593 (The Pile)

Max Activating Token Index: 369

Text #13

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2151. Min Act: -0.0000

Data Index: 553858 (The Pile)

Max Activating Token Index: 913

Text #14

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.1917. Min Act: -0.0000

Data Index: 1225699 (The Pile)

Max Activating Token Index: 49

Text #15

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2186. Min Act: -0.0000

Data Index: 612532 (The Pile)

Max Activating Token Index: 761

Text #16

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2227. Min Act: -0.0000

Data Index: 556529 (The Pile)

Max Activating Token Index: 16

Text #17

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2063. Min Act: -0.0000

Data Index: 389765 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1468484 (The Pile)

Max Activating Token Index: 722

Text #19

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2238. Min Act: -0.0000

Data Index: 869114 (The Pile)

Max Activating Token Index: 605