Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3040 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 1.0351. Min Range: -1.0351

Max Act: 1.0351. Min Act: -0.0000

Data Index: 99532 (The Pile)

Max Activating Token Index: 466

Text #1

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.9805. Min Act: -0.0000

Data Index: 1146536 (The Pile)

Max Activating Token Index: 628

Text #2

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.9755. Min Act: -0.0000

Data Index: 673035 (The Pile)

Max Activating Token Index: 436

Text #3

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.9343. Min Act: -0.0001

Data Index: 694540 (The Pile)

Max Activating Token Index: 450

Text #4

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.9269. Min Act: -0.0000

Data Index: 258518 (The Pile)

Max Activating Token Index: 604

Text #5

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.9486. Min Act: -0.0000

Data Index: 1794203 (The Pile)

Max Activating Token Index: 555

Text #6

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.9407. Min Act: -0.0000

Data Index: 1146875 (The Pile)

Max Activating Token Index: 430

Text #7

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.8636. Min Act: -0.0000

Data Index: 167992 (The Pile)

Max Activating Token Index: 910

Text #8

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.8917. Min Act: -0.0000

Data Index: 322686 (The Pile)

Max Activating Token Index: 466

Text #9

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.9151. Min Act: -0.0001

Data Index: 816434 (The Pile)

Max Activating Token Index: 438

Text #10

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.9453. Min Act: -0.0000

Data Index: 875864 (The Pile)

Max Activating Token Index: 429

Text #11

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.9058. Min Act: -0.0000

Data Index: 1138020 (The Pile)

Max Activating Token Index: 583

Text #12

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.9127. Min Act: -0.0000

Data Index: 902198 (The Pile)

Max Activating Token Index: 492

Text #13

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.9045. Min Act: -0.0001

Data Index: 1667328 (The Pile)

Max Activating Token Index: 389

Text #14

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.9186. Min Act: -0.0001

Data Index: 1546025 (The Pile)

Max Activating Token Index: 168

Text #15

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.9192. Min Act: -0.0000

Data Index: 450960 (The Pile)

Max Activating Token Index: 589

Text #16

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.8861. Min Act: -0.0000

Data Index: 962398 (The Pile)

Max Activating Token Index: 387

Text #17

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1399937 (The Pile)

Max Activating Token Index: 393

Text #18

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.8872. Min Act: -0.0000

Data Index: 71599 (The Pile)

Max Activating Token Index: 430

Text #19

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.8807. Min Act: -0.0000

Data Index: 808222 (The Pile)

Max Activating Token Index: 488