Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 707 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.3954. Min Act: -0.0000

Data Index: 355632 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 3.4364. Min Range: -3.4364

Max Act: 3.4364. Min Act: -0.0000

Data Index: 1064192 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 3.4364. Min Range: -3.4364

Max Act: 2.8563. Min Act: -0.0000

Data Index: 32191 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 3.4364. Min Range: -3.4364

Max Act: 1.1651. Min Act: -0.0000

Data Index: 131928 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 3.4364. Min Range: -3.4364

Max Act: 1.0318. Min Act: -0.0000

Data Index: 318368 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 3.4364. Min Range: -3.4364

Max Act: 0.8583. Min Act: -0.0000

Data Index: 675658 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 3.4364. Min Range: -3.4364

Max Act: 0.7612. Min Act: -0.0000

Data Index: 854834 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 3.4364. Min Range: -3.4364

Max Act: 0.7700. Min Act: -0.0000

Data Index: 40374 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 3.4364. Min Range: -3.4364

Max Act: 0.6465. Min Act: -0.0000

Data Index: 358443 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 3.4364. Min Range: -3.4364

Max Act: 0.7272. Min Act: -0.0000

Data Index: 141042 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 3.4364. Min Range: -3.4364

Max Act: 0.6855. Min Act: -0.0001

Data Index: 251917 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 3.4364. Min Range: -3.4364

Max Act: 0.7213. Min Act: -0.0001

Data Index: 408740 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 3.4364. Min Range: -3.4364

Max Act: 0.5790. Min Act: -0.0000

Data Index: 744255 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 3.4364. Min Range: -3.4364

Max Act: 0.6099. Min Act: -0.0000

Data Index: 777317 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 3.4364. Min Range: -3.4364

Max Act: 0.7301. Min Act: -0.0000

Data Index: 520262 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 3.4364. Min Range: -3.4364

Max Act: 0.6632. Min Act: -0.0000

Data Index: 833479 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 3.4364. Min Range: -3.4364

Max Act: 0.6171. Min Act: -0.0000

Data Index: 55063 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 3.4364. Min Range: -3.4364

Max Act: 0.6260. Min Act: -0.0000

Data Index: 1288686 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 3.4364. Min Range: -3.4364

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1257119 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 3.4364. Min Range: -3.4364

Max Act: 0.6450. Min Act: -0.0000

Data Index: 815723 (C4 (Web Text))

Max Activating Token Index: 90