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

Dataset: The Pile

Neuron 466 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: 0.6763. Min Range: -0.6763

Max Act: 0.6763. Min Act: -0.0000

Data Index: 676288 (The Pile)

Max Activating Token Index: 111

Text #1

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.4880. Min Act: -0.0000

Data Index: 816919 (The Pile)

Max Activating Token Index: 151

Text #2

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.4231. Min Act: -0.0000

Data Index: 1543339 (The Pile)

Max Activating Token Index: 950

Text #3

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.4203. Min Act: -0.0000

Data Index: 1794573 (The Pile)

Max Activating Token Index: 560

Text #4

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.4179. Min Act: -0.0000

Data Index: 274101 (The Pile)

Max Activating Token Index: 249

Text #5

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.3534. Min Act: -0.0000

Data Index: 316027 (The Pile)

Max Activating Token Index: 816

Text #6

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1457634 (The Pile)

Max Activating Token Index: 283

Text #7

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.3602. Min Act: -0.0000

Data Index: 1671978 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.3554. Min Act: -0.0000

Data Index: 1072571 (The Pile)

Max Activating Token Index: 260

Text #9

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.3796. Min Act: -0.0000

Data Index: 341879 (The Pile)

Max Activating Token Index: 791

Text #10

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.3210. Min Act: -0.0000

Data Index: 1844351 (The Pile)

Max Activating Token Index: 349

Text #11

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.3521. Min Act: -0.0000

Data Index: 1075910 (The Pile)

Max Activating Token Index: 1022

Text #12

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.3627. Min Act: -0.0000

Data Index: 1798268 (The Pile)

Max Activating Token Index: 885

Text #13

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1353448 (The Pile)

Max Activating Token Index: 352

Text #14

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.3411. Min Act: -0.0000

Data Index: 1263567 (The Pile)

Max Activating Token Index: 493

Text #15

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.3387. Min Act: -0.0000

Data Index: 835388 (The Pile)

Max Activating Token Index: 428

Text #16

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.3280. Min Act: -0.0000

Data Index: 653029 (The Pile)

Max Activating Token Index: 435

Text #17

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.3169. Min Act: -0.0000

Data Index: 1921375 (The Pile)

Max Activating Token Index: 284

Text #18

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.2940. Min Act: -0.0000

Data Index: 1015125 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.3068. Min Act: -0.0000

Data Index: 1885028 (The Pile)

Max Activating Token Index: 925