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

Dataset: The Pile

Neuron 3139 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: 1.5385. Min Range: -1.5385

Max Act: 1.5385. Min Act: -0.0000

Data Index: 1667998 (The Pile)

Max Activating Token Index: 538

Text #1

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.3657. Min Act: -0.0000

Data Index: 1955433 (The Pile)

Max Activating Token Index: 53

Text #2

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.1883. Min Act: -0.0000

Data Index: 1308588 (The Pile)

Max Activating Token Index: 221

Text #3

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.2217. Min Act: -0.0000

Data Index: 109400 (The Pile)

Max Activating Token Index: 580

Text #4

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.2013. Min Act: -0.0000

Data Index: 321970 (The Pile)

Max Activating Token Index: 261

Text #5

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.1944. Min Act: -0.0000

Data Index: 1826691 (The Pile)

Max Activating Token Index: 781

Text #6

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.0578. Min Act: -0.0000

Data Index: 373000 (The Pile)

Max Activating Token Index: 1022

Text #7

Max Range: 1.5385. Min Range: -1.5385

Max Act: 0.9389. Min Act: -0.0000

Data Index: 670094 (The Pile)

Max Activating Token Index: 662

Text #8

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.0482. Min Act: -0.0000

Data Index: 321076 (The Pile)

Max Activating Token Index: 596

Text #9

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.0965. Min Act: -0.0000

Data Index: 566124 (The Pile)

Max Activating Token Index: 422

Text #10

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.1397. Min Act: -0.0000

Data Index: 1930109 (The Pile)

Max Activating Token Index: 457

Text #11

Max Range: 1.5385. Min Range: -1.5385

Max Act: 0.9892. Min Act: -0.0000

Data Index: 1620165 (The Pile)

Max Activating Token Index: 947

Text #12

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.0808. Min Act: -0.0000

Data Index: 1795492 (The Pile)

Max Activating Token Index: 549

Text #13

Max Range: 1.5385. Min Range: -1.5385

Max Act: 0.9626. Min Act: -0.0000

Data Index: 1103015 (The Pile)

Max Activating Token Index: 445

Text #14

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.0469. Min Act: -0.0000

Data Index: 867895 (The Pile)

Max Activating Token Index: 171

Text #15

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.0543. Min Act: -0.0000

Data Index: 1416653 (The Pile)

Max Activating Token Index: 668

Text #16

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.0324. Min Act: -0.0000

Data Index: 90088 (The Pile)

Max Activating Token Index: 343

Text #17

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.0154. Min Act: -0.0000

Data Index: 1206084 (The Pile)

Max Activating Token Index: 404

Text #18

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.0356. Min Act: -0.0000

Data Index: 305162 (The Pile)

Max Activating Token Index: 780

Text #19

Max Range: 1.5385. Min Range: -1.5385

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1200745 (The Pile)

Max Activating Token Index: 1001