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

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

Neuron 1079 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 13.6711. Min Range: -13.6711

Max Act: 13.6711. Min Act: -0.0000

Data Index: 1026952 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 13.6711. Min Range: -13.6711

Max Act: 13.6470. Min Act: -0.0000

Data Index: 119420 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 13.6711. Min Range: -13.6711

Max Act: 12.5452. Min Act: -0.0000

Data Index: 1312815 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 13.6711. Min Range: -13.6711

Max Act: 0.0125. Min Act: -0.0000

Data Index: 243404 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 13.6711. Min Range: -13.6711

Max Act: 0.0105. Min Act: -0.0000

Data Index: 1097468 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 13.6711. Min Range: -13.6711

Max Act: 0.5847. Min Act: -0.0000

Data Index: 821938 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 13.6711. Min Range: -13.6711

Max Act: 0.9317. Min Act: -0.0000

Data Index: 38584 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 13.6711. Min Range: -13.6711

Max Act: 0.0118. Min Act: -0.0000

Data Index: 1275402 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 13.6711. Min Range: -13.6711

Max Act: 0.1726. Min Act: -0.0000

Data Index: 1094987 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 13.6711. Min Range: -13.6711

Max Act: 0.0390. Min Act: -0.0000

Data Index: 347171 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 13.6711. Min Range: -13.6711

Max Act: 0.1598. Min Act: -0.0000

Data Index: 487278 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 13.6711. Min Range: -13.6711

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1080356 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 13.6711. Min Range: -13.6711

Max Act: 0.0402. Min Act: -0.0000

Data Index: 934868 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 13.6711. Min Range: -13.6711

Max Act: 0.0491. Min Act: -0.0000

Data Index: 400775 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 13.6711. Min Range: -13.6711

Max Act: 0.1397. Min Act: -0.0000

Data Index: 229565 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 13.6711. Min Range: -13.6711

Max Act: 0.1271. Min Act: -0.0000

Data Index: 390963 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 13.6711. Min Range: -13.6711

Max Act: 0.1356. Min Act: -0.0000

Data Index: 103820 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 13.6711. Min Range: -13.6711

Max Act: 0.0115. Min Act: -0.0000

Data Index: 796665 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 13.6711. Min Range: -13.6711

Max Act: 0.1088. Min Act: -0.0000

Data Index: 417270 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 13.6711. Min Range: -13.6711

Max Act: 0.1232. Min Act: -0.0000

Data Index: 555440 (C4 (Web Text))

Max Activating Token Index: 347