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

Dataset: The Pile

Neuron 2540 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.4096. Min Act: -0.0000

Data Index: 530392 (The Pile)

Max Activating Token Index: 403

Text #1

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2903. Min Act: -0.0000

Data Index: 1193095 (The Pile)

Max Activating Token Index: 810

Text #2

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1366882 (The Pile)

Max Activating Token Index: 462

Text #3

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2864. Min Act: -0.0000

Data Index: 62324 (The Pile)

Max Activating Token Index: 711

Text #4

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1287923 (The Pile)

Max Activating Token Index: 789

Text #5

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.3010. Min Act: -0.0000

Data Index: 201139 (The Pile)

Max Activating Token Index: 142

Text #6

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2703. Min Act: -0.0000

Data Index: 1610260 (The Pile)

Max Activating Token Index: 322

Text #7

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2341. Min Act: -0.0000

Data Index: 497843 (The Pile)

Max Activating Token Index: 894

Text #8

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2792. Min Act: -0.0000

Data Index: 265537 (The Pile)

Max Activating Token Index: 456

Text #9

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2615. Min Act: -0.0000

Data Index: 1147945 (The Pile)

Max Activating Token Index: 161

Text #10

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1207051 (The Pile)

Max Activating Token Index: 733

Text #11

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1534748 (The Pile)

Max Activating Token Index: 733

Text #12

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2353. Min Act: -0.0000

Data Index: 1727052 (The Pile)

Max Activating Token Index: 557

Text #13

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2489. Min Act: -0.0000

Data Index: 1695258 (The Pile)

Max Activating Token Index: 688

Text #14

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2413. Min Act: -0.0000

Data Index: 1253260 (The Pile)

Max Activating Token Index: 442

Text #15

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1214907 (The Pile)

Max Activating Token Index: 454

Text #16

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2509. Min Act: -0.0000

Data Index: 1934999 (The Pile)

Max Activating Token Index: 531

Text #17

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2323. Min Act: -0.0000

Data Index: 587202 (The Pile)

Max Activating Token Index: 754

Text #18

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2683. Min Act: -0.0000

Data Index: 1634246 (The Pile)

Max Activating Token Index: 635

Text #19

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2299. Min Act: -0.0000

Data Index: 1985233 (The Pile)

Max Activating Token Index: 845