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

Dataset: The Pile

Neuron 2403 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: 4.4141. Min Range: -4.4141

Max Act: 4.4141. Min Act: -0.0000

Data Index: 1416905 (The Pile)

Max Activating Token Index: 458

Text #1

Max Range: 4.4141. Min Range: -4.4141

Max Act: 4.2433. Min Act: -0.0000

Data Index: 1332807 (The Pile)

Max Activating Token Index: 686

Text #2

Max Range: 4.4141. Min Range: -4.4141

Max Act: 3.8634. Min Act: -0.0000

Data Index: 360226 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 4.4141. Min Range: -4.4141

Max Act: 3.8297. Min Act: -0.0000

Data Index: 234507 (The Pile)

Max Activating Token Index: 489

Text #4

Max Range: 4.4141. Min Range: -4.4141

Max Act: 3.5789. Min Act: -0.0000

Data Index: 84229 (The Pile)

Max Activating Token Index: 759

Text #5

Max Range: 4.4141. Min Range: -4.4141

Max Act: 3.5390. Min Act: -0.0000

Data Index: 442881 (The Pile)

Max Activating Token Index: 358

Text #6

Max Range: 4.4141. Min Range: -4.4141

Max Act: 3.7583. Min Act: -0.0000

Data Index: 142420 (The Pile)

Max Activating Token Index: 186

Text #7

Max Range: 4.4141. Min Range: -4.4141

Max Act: 3.6106. Min Act: -0.0000

Data Index: 1387574 (The Pile)

Max Activating Token Index: 144

Text #8

Max Range: 4.4141. Min Range: -4.4141

Max Act: 4.1234. Min Act: -0.0000

Data Index: 1980283 (The Pile)

Max Activating Token Index: 803

Text #9

Max Range: 4.4141. Min Range: -4.4141

Max Act: 3.2816. Min Act: -0.0000

Data Index: 420743 (The Pile)

Max Activating Token Index: 833

Text #10

Max Range: 4.4141. Min Range: -4.4141

Max Act: 3.5380. Min Act: -0.0000

Data Index: 1429750 (The Pile)

Max Activating Token Index: 293

Text #11

Max Range: 4.4141. Min Range: -4.4141

Max Act: 3.2576. Min Act: -0.0000

Data Index: 957385 (The Pile)

Max Activating Token Index: 194

Text #12

Max Range: 4.4141. Min Range: -4.4141

Max Act: 3.2271. Min Act: -0.0000

Data Index: 1238189 (The Pile)

Max Activating Token Index: 963

Text #13

Max Range: 4.4141. Min Range: -4.4141

Max Act: 3.1257. Min Act: -0.0000

Data Index: 1187808 (The Pile)

Max Activating Token Index: 417

Text #14

Max Range: 4.4141. Min Range: -4.4141

Max Act: 3.2885. Min Act: -0.0000

Data Index: 430155 (The Pile)

Max Activating Token Index: 680

Text #15

Max Range: 4.4141. Min Range: -4.4141

Max Act: 3.1041. Min Act: -0.0000

Data Index: 1543239 (The Pile)

Max Activating Token Index: 186

Text #16

Max Range: 4.4141. Min Range: -4.4141

Max Act: 2.9558. Min Act: -0.0000

Data Index: 1669588 (The Pile)

Max Activating Token Index: 169

Text #17

Max Range: 4.4141. Min Range: -4.4141

Max Act: 2.8456. Min Act: -0.0000

Data Index: 1468974 (The Pile)

Max Activating Token Index: 573

Text #18

Max Range: 4.4141. Min Range: -4.4141

Max Act: 3.1186. Min Act: -0.0000

Data Index: 790732 (The Pile)

Max Activating Token Index: 248

Text #19

Max Range: 4.4141. Min Range: -4.4141

Max Act: 2.9344. Min Act: -0.0000

Data Index: 1813163 (The Pile)

Max Activating Token Index: 550