Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3780 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 4.3617. Min Range: -4.3617

Max Act: 4.3617. Min Act: -0.0000

Data Index: 820016 (The Pile)

Max Activating Token Index: 201

Text #1

Max Range: 4.3617. Min Range: -4.3617

Max Act: 3.7362. Min Act: -0.0000

Data Index: 1107866 (The Pile)

Max Activating Token Index: 609

Text #2

Max Range: 4.3617. Min Range: -4.3617

Max Act: 3.3958. Min Act: -0.0000

Data Index: 1488145 (The Pile)

Max Activating Token Index: 808

Text #3

Max Range: 4.3617. Min Range: -4.3617

Max Act: 3.2401. Min Act: -0.0000

Data Index: 1678548 (The Pile)

Max Activating Token Index: 622

Text #4

Max Range: 4.3617. Min Range: -4.3617

Max Act: 3.3601. Min Act: -0.0000

Data Index: 1467017 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 4.3617. Min Range: -4.3617

Max Act: 3.3343. Min Act: -0.0000

Data Index: 568685 (The Pile)

Max Activating Token Index: 618

Text #6

Max Range: 4.3617. Min Range: -4.3617

Max Act: 3.6121. Min Act: -0.0000

Data Index: 1673992 (The Pile)

Max Activating Token Index: 263

Text #7

Max Range: 4.3617. Min Range: -4.3617

Max Act: 3.3966. Min Act: -0.0000

Data Index: 1219829 (The Pile)

Max Activating Token Index: 692

Text #8

Max Range: 4.3617. Min Range: -4.3617

Max Act: 3.1538. Min Act: -0.0000

Data Index: 727601 (The Pile)

Max Activating Token Index: 299

Text #9

Max Range: 4.3617. Min Range: -4.3617

Max Act: 3.2243. Min Act: -0.0000

Data Index: 1928829 (The Pile)

Max Activating Token Index: 335

Text #10

Max Range: 4.3617. Min Range: -4.3617

Max Act: 3.1901. Min Act: -0.0000

Data Index: 1862089 (The Pile)

Max Activating Token Index: 832

Text #11

Max Range: 4.3617. Min Range: -4.3617

Max Act: 3.0740. Min Act: -0.0000

Data Index: 1931174 (The Pile)

Max Activating Token Index: 493

Text #12

Max Range: 4.3617. Min Range: -4.3617

Max Act: 3.2322. Min Act: -0.0000

Data Index: 1159182 (The Pile)

Max Activating Token Index: 753

Text #13

Max Range: 4.3617. Min Range: -4.3617

Max Act: 2.9364. Min Act: -0.0000

Data Index: 451847 (The Pile)

Max Activating Token Index: 174

Text #14

Max Range: 4.3617. Min Range: -4.3617

Max Act: 2.9372. Min Act: -0.0000

Data Index: 390498 (The Pile)

Max Activating Token Index: 862

Text #15

Max Range: 4.3617. Min Range: -4.3617

Max Act: 3.2163. Min Act: -0.0000

Data Index: 1310522 (The Pile)

Max Activating Token Index: 470

Text #16

Max Range: 4.3617. Min Range: -4.3617

Max Act: 2.8881. Min Act: -0.0000

Data Index: 472248 (The Pile)

Max Activating Token Index: 521

Text #17

Max Range: 4.3617. Min Range: -4.3617

Max Act: 3.0413. Min Act: -0.0000

Data Index: 1140772 (The Pile)

Max Activating Token Index: 373

Text #18

Max Range: 4.3617. Min Range: -4.3617

Max Act: 3.0425. Min Act: -0.0000

Data Index: 464671 (The Pile)

Max Activating Token Index: 9

Text #19

Max Range: 4.3617. Min Range: -4.3617

Max Act: 3.0226. Min Act: -0.0000

Data Index: 1827350 (The Pile)

Max Activating Token Index: 462