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

Dataset: The Pile

Neuron 1080 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.8041. Min Act: -0.0000

Data Index: 380980 (The Pile)

Max Activating Token Index: 754

Text #1

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1872238 (The Pile)

Max Activating Token Index: 358

Text #2

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.3972. Min Act: -0.0000

Data Index: 1748596 (The Pile)

Max Activating Token Index: 919

Text #3

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.4588. Min Act: -0.0000

Data Index: 839394 (The Pile)

Max Activating Token Index: 520

Text #4

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.4641. Min Act: -0.0000

Data Index: 532990 (The Pile)

Max Activating Token Index: 330

Text #5

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.3819. Min Act: -0.0000

Data Index: 243423 (The Pile)

Max Activating Token Index: 557

Text #6

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.4358. Min Act: -0.0000

Data Index: 1694271 (The Pile)

Max Activating Token Index: 124

Text #7

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.4174. Min Act: -0.0000

Data Index: 458688 (The Pile)

Max Activating Token Index: 412

Text #8

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.4294. Min Act: -0.0000

Data Index: 960398 (The Pile)

Max Activating Token Index: 248

Text #9

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.4259. Min Act: -0.0000

Data Index: 433195 (The Pile)

Max Activating Token Index: 510

Text #10

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1486419 (The Pile)

Max Activating Token Index: 870

Text #11

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1508317 (The Pile)

Max Activating Token Index: 707

Text #12

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1689829 (The Pile)

Max Activating Token Index: 41

Text #13

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.4315. Min Act: -0.0000

Data Index: 113334 (The Pile)

Max Activating Token Index: 416

Text #14

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.4182. Min Act: -0.0000

Data Index: 956336 (The Pile)

Max Activating Token Index: 511

Text #15

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.4264. Min Act: -0.0000

Data Index: 926439 (The Pile)

Max Activating Token Index: 70

Text #16

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1627475 (The Pile)

Max Activating Token Index: 137

Text #17

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.3930. Min Act: -0.0000

Data Index: 400515 (The Pile)

Max Activating Token Index: 583

Text #18

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.3912. Min Act: -0.0000

Data Index: 424643 (The Pile)

Max Activating Token Index: 422

Text #19

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.4158. Min Act: -0.0000

Data Index: 909789 (The Pile)

Max Activating Token Index: 524