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

Dataset: The Pile

Neuron 36 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9543. Min Range: -3.9543

Max Act: 3.9533. Min Act: -0.0000

Data Index: 546794 (The Pile)

Max Activating Token Index: 256

Text #1

Max Range: 3.9543. Min Range: -3.9543

Max Act: 3.9543. Min Act: -0.0000

Data Index: 1441823 (The Pile)

Max Activating Token Index: 508

Text #2

Max Range: 3.9543. Min Range: -3.9543

Max Act: 3.8768. Min Act: -0.0000

Data Index: 257143 (The Pile)

Max Activating Token Index: 555

Text #3

Max Range: 3.9543. Min Range: -3.9543

Max Act: 3.6308. Min Act: -0.0000

Data Index: 1232950 (The Pile)

Max Activating Token Index: 310

Text #4

Max Range: 3.9543. Min Range: -3.9543

Max Act: 3.7660. Min Act: -0.0000

Data Index: 833939 (The Pile)

Max Activating Token Index: 170

Text #5

Max Range: 3.9543. Min Range: -3.9543

Max Act: 3.5459. Min Act: -0.0000

Data Index: 1521253 (The Pile)

Max Activating Token Index: 437

Text #6

Max Range: 3.9543. Min Range: -3.9543

Max Act: 3.5149. Min Act: -0.0000

Data Index: 1448286 (The Pile)

Max Activating Token Index: 248

Text #7

Max Range: 3.9543. Min Range: -3.9543

Max Act: 3.6618. Min Act: -0.0000

Data Index: 1982687 (The Pile)

Max Activating Token Index: 475

Text #8

Max Range: 3.9543. Min Range: -3.9543

Max Act: 3.4308. Min Act: -0.0000

Data Index: 1535854 (The Pile)

Max Activating Token Index: 672

Text #9

Max Range: 3.9543. Min Range: -3.9543

Max Act: 3.4024. Min Act: -0.0000

Data Index: 16720 (The Pile)

Max Activating Token Index: 391

Text #10

Max Range: 3.9543. Min Range: -3.9543

Max Act: 3.3732. Min Act: -0.0000

Data Index: 367111 (The Pile)

Max Activating Token Index: 184

Text #11

Max Range: 3.9543. Min Range: -3.9543

Max Act: 3.0252. Min Act: -0.0000

Data Index: 1890705 (The Pile)

Max Activating Token Index: 213

Text #12

Max Range: 3.9543. Min Range: -3.9543

Max Act: 3.4873. Min Act: -0.0000

Data Index: 422791 (The Pile)

Max Activating Token Index: 326

Text #13

Max Range: 3.9543. Min Range: -3.9543

Max Act: 3.3139. Min Act: -0.0000

Data Index: 924513 (The Pile)

Max Activating Token Index: 454

Text #14

Max Range: 3.9543. Min Range: -3.9543

Max Act: 3.1741. Min Act: -0.0000

Data Index: 1200532 (The Pile)

Max Activating Token Index: 148

Text #15

Max Range: 3.9543. Min Range: -3.9543

Max Act: 3.1216. Min Act: -0.0000

Data Index: 455201 (The Pile)

Max Activating Token Index: 209

Text #16

Max Range: 3.9543. Min Range: -3.9543

Max Act: 3.4292. Min Act: -0.0000

Data Index: 1972142 (The Pile)

Max Activating Token Index: 257

Text #17

Max Range: 3.9543. Min Range: -3.9543

Max Act: 3.5405. Min Act: -0.0000

Data Index: 828141 (The Pile)

Max Activating Token Index: 330

Text #18

Max Range: 3.9543. Min Range: -3.9543

Max Act: 3.2330. Min Act: -0.0000

Data Index: 630461 (The Pile)

Max Activating Token Index: 243

Text #19

Max Range: 3.9543. Min Range: -3.9543

Max Act: 3.2374. Min Act: -0.0000

Data Index: 802969 (The Pile)

Max Activating Token Index: 591