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

Dataset: The Pile

Neuron 290 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.7266. Min Act: -0.0000

Data Index: 1067339 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5443. Min Act: 0.0000

Data Index: 1201182 (The Pile)

Max Activating Token Index: 107

Text #2

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5443. Min Act: -0.0000

Data Index: 115830 (The Pile)

Max Activating Token Index: 178

Text #3

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5365. Min Act: -0.0000

Data Index: 842466 (The Pile)

Max Activating Token Index: 434

Text #4

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5180. Min Act: -0.0000

Data Index: 1494156 (The Pile)

Max Activating Token Index: 371

Text #5

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1411300 (The Pile)

Max Activating Token Index: 356

Text #6

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.5128. Min Act: -0.0000

Data Index: 1809210 (The Pile)

Max Activating Token Index: 1003

Text #7

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4644. Min Act: -0.0000

Data Index: 355946 (The Pile)

Max Activating Token Index: 189

Text #8

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4481. Min Act: -0.0000

Data Index: 1633524 (The Pile)

Max Activating Token Index: 407

Text #9

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4626. Min Act: -0.0000

Data Index: 483187 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4442. Min Act: -0.0000

Data Index: 233809 (The Pile)

Max Activating Token Index: 680

Text #11

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4396. Min Act: -0.0000

Data Index: 859945 (The Pile)

Max Activating Token Index: 751

Text #12

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4327. Min Act: -0.0000

Data Index: 1683560 (The Pile)

Max Activating Token Index: 137

Text #13

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4419. Min Act: -0.0000

Data Index: 296238 (The Pile)

Max Activating Token Index: 215

Text #14

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4487. Min Act: -0.0000

Data Index: 1286717 (The Pile)

Max Activating Token Index: 165

Text #15

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4320. Min Act: -0.0000

Data Index: 1571483 (The Pile)

Max Activating Token Index: 76

Text #16

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4146. Min Act: -0.0000

Data Index: 776550 (The Pile)

Max Activating Token Index: 143

Text #17

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4127. Min Act: 0.0000

Data Index: 1024145 (The Pile)

Max Activating Token Index: 669

Text #18

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4368. Min Act: -0.0000

Data Index: 680806 (The Pile)

Max Activating Token Index: 218

Text #19

Max Range: 0.7266. Min Range: -0.7266

Max Act: 0.4119. Min Act: -0.0000

Data Index: 121192 (The Pile)

Max Activating Token Index: 511