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

Dataset: The Pile

Neuron 3458 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0380. Min Range: -1.0380

Max Act: 1.0380. Min Act: -0.0001

Data Index: 1210995 (The Pile)

Max Activating Token Index: 953

Text #1

Max Range: 1.0380. Min Range: -1.0380

Max Act: 1.0267. Min Act: -0.0000

Data Index: 443448 (The Pile)

Max Activating Token Index: 33

Text #2

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.8968. Min Act: -0.0000

Data Index: 1514651 (The Pile)

Max Activating Token Index: 486

Text #3

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.9224. Min Act: -0.0000

Data Index: 408253 (The Pile)

Max Activating Token Index: 856

Text #4

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.9700. Min Act: -0.0000

Data Index: 912511 (The Pile)

Max Activating Token Index: 887

Text #5

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.8707. Min Act: 0.0000

Data Index: 212695 (The Pile)

Max Activating Token Index: 206

Text #6

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1160213 (The Pile)

Max Activating Token Index: 365

Text #7

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.9240. Min Act: -0.0000

Data Index: 1678171 (The Pile)

Max Activating Token Index: 651

Text #8

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.8468. Min Act: -0.0000

Data Index: 1448418 (The Pile)

Max Activating Token Index: 53

Text #9

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.9280. Min Act: -0.0000

Data Index: 1277721 (The Pile)

Max Activating Token Index: 223

Text #10

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.9324. Min Act: -0.0000

Data Index: 1741380 (The Pile)

Max Activating Token Index: 758

Text #11

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.6286. Min Act: -0.0000

Data Index: 1211248 (The Pile)

Max Activating Token Index: 77

Text #12

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.8876. Min Act: -0.0000

Data Index: 133259 (The Pile)

Max Activating Token Index: 82

Text #13

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.8418. Min Act: 0.0001

Data Index: 182402 (The Pile)

Max Activating Token Index: 920

Text #14

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.6736. Min Act: -0.0000

Data Index: 127456 (The Pile)

Max Activating Token Index: 1020

Text #15

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1931656 (The Pile)

Max Activating Token Index: 770

Text #16

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.8303. Min Act: 0.0000

Data Index: 1310700 (The Pile)

Max Activating Token Index: 154

Text #17

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.7564. Min Act: -0.0000

Data Index: 658161 (The Pile)

Max Activating Token Index: 428

Text #18

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.8229. Min Act: -0.0000

Data Index: 1394039 (The Pile)

Max Activating Token Index: 836

Text #19

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.7212. Min Act: -0.0000

Data Index: 1880363 (The Pile)

Max Activating Token Index: 920