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

Dataset: The Pile

Neuron 2045 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: 1.4167. Min Range: -1.4167

Max Act: 1.4167. Min Act: -0.0000

Data Index: 282042 (The Pile)

Max Activating Token Index: 661

Text #1

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.2368. Min Act: -0.0000

Data Index: 601755 (The Pile)

Max Activating Token Index: 309

Text #2

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.2804. Min Act: -0.0000

Data Index: 1637812 (The Pile)

Max Activating Token Index: 436

Text #3

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.1924. Min Act: -0.0000

Data Index: 1397680 (The Pile)

Max Activating Token Index: 74

Text #4

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.0891. Min Act: -0.0000

Data Index: 1516453 (The Pile)

Max Activating Token Index: 259

Text #5

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.0971. Min Act: -0.0000

Data Index: 1303465 (The Pile)

Max Activating Token Index: 404

Text #6

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.0937. Min Act: -0.0000

Data Index: 490539 (The Pile)

Max Activating Token Index: 62

Text #7

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.0213. Min Act: -0.0000

Data Index: 1977748 (The Pile)

Max Activating Token Index: 477

Text #8

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.0720. Min Act: -0.0000

Data Index: 672965 (The Pile)

Max Activating Token Index: 249

Text #9

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.0577. Min Act: -0.0000

Data Index: 1878468 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1905198 (The Pile)

Max Activating Token Index: 205

Text #11

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.0399. Min Act: -0.0000

Data Index: 672698 (The Pile)

Max Activating Token Index: 866

Text #12

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.0055. Min Act: -0.0000

Data Index: 1944356 (The Pile)

Max Activating Token Index: 443

Text #13

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.0316. Min Act: -0.0000

Data Index: 1395987 (The Pile)

Max Activating Token Index: 570

Text #14

Max Range: 1.4167. Min Range: -1.4167

Max Act: 0.9956. Min Act: -0.0000

Data Index: 850802 (The Pile)

Max Activating Token Index: 633

Text #15

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.0206. Min Act: -0.0000

Data Index: 483309 (The Pile)

Max Activating Token Index: 874

Text #16

Max Range: 1.4167. Min Range: -1.4167

Max Act: 1.0497. Min Act: -0.0000

Data Index: 1412144 (The Pile)

Max Activating Token Index: 987

Text #17

Max Range: 1.4167. Min Range: -1.4167

Max Act: 0.9952. Min Act: -0.0000

Data Index: 827094 (The Pile)

Max Activating Token Index: 220

Text #18

Max Range: 1.4167. Min Range: -1.4167

Max Act: 0.9683. Min Act: -0.0000

Data Index: 562198 (The Pile)

Max Activating Token Index: 606

Text #19

Max Range: 1.4167. Min Range: -1.4167

Max Act: 0.9897. Min Act: -0.0000

Data Index: 259968 (The Pile)

Max Activating Token Index: 431