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

Dataset: The Pile

Neuron 1042 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: 1.1319. Min Range: -1.1319

Max Act: 1.1319. Min Act: -0.0000

Data Index: 1070650 (The Pile)

Max Activating Token Index: 80

Text #1

Max Range: 1.1319. Min Range: -1.1319

Max Act: 1.0367. Min Act: -0.0000

Data Index: 755862 (The Pile)

Max Activating Token Index: 227

Text #2

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1531111 (The Pile)

Max Activating Token Index: 124

Text #3

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.9205. Min Act: -0.0000

Data Index: 1202840 (The Pile)

Max Activating Token Index: 444

Text #4

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.9053. Min Act: -0.0000

Data Index: 1785870 (The Pile)

Max Activating Token Index: 617

Text #5

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.9027. Min Act: -0.0000

Data Index: 1583485 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.9083. Min Act: -0.0000

Data Index: 1160340 (The Pile)

Max Activating Token Index: 208

Text #7

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.8762. Min Act: -0.0000

Data Index: 258721 (The Pile)

Max Activating Token Index: 588

Text #8

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1238462 (The Pile)

Max Activating Token Index: 93

Text #9

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.8871. Min Act: -0.0000

Data Index: 1393313 (The Pile)

Max Activating Token Index: 208

Text #10

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1181227 (The Pile)

Max Activating Token Index: 630

Text #11

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.8558. Min Act: -0.0000

Data Index: 1450367 (The Pile)

Max Activating Token Index: 14

Text #12

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.8536. Min Act: -0.0000

Data Index: 1438410 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.8328. Min Act: -0.0000

Data Index: 48019 (The Pile)

Max Activating Token Index: 652

Text #14

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.8131. Min Act: -0.0000

Data Index: 1662868 (The Pile)

Max Activating Token Index: 197

Text #15

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.7799. Min Act: -0.0000

Data Index: 1044092 (The Pile)

Max Activating Token Index: 549

Text #16

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.7869. Min Act: -0.0000

Data Index: 1663704 (The Pile)

Max Activating Token Index: 549

Text #17

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.8003. Min Act: -0.0000

Data Index: 1928184 (The Pile)

Max Activating Token Index: 71

Text #18

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.8130. Min Act: -0.0000

Data Index: 981424 (The Pile)

Max Activating Token Index: 884

Text #19

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.8188. Min Act: -0.0000

Data Index: 1786184 (The Pile)

Max Activating Token Index: 26