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

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

Neuron 1152 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.7732. Min Act: -0.0003

Data Index: 459085 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.8416. Min Act: -0.0003

Data Index: 665761 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.8593. Min Act: -0.0003

Data Index: 690880 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6987. Min Act: -0.0003

Data Index: 493647 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.8495. Min Act: -0.0003

Data Index: 1334038 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6460. Min Act: -0.0003

Data Index: 713898 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.9397. Min Act: -0.0003

Data Index: 513643 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.7986. Min Act: -0.0003

Data Index: 421090 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.8455. Min Act: -0.0003

Data Index: 884173 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.8181. Min Act: -0.0003

Data Index: 372139 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.8943. Min Act: -0.0003

Data Index: 585231 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.8407. Min Act: -0.0003

Data Index: 485153 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.8464. Min Act: -0.0003

Data Index: 259485 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.8914. Min Act: -0.0003

Data Index: 598727 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.9251. Min Act: -0.0003

Data Index: 785448 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.7854. Min Act: -0.0003

Data Index: 722710 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.7309. Min Act: -0.0003

Data Index: 1107139 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.8823. Min Act: -0.0003

Data Index: 391590 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.9103. Min Act: -0.0003

Data Index: 827733 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.8811. Min Act: -0.0003

Data Index: 1027700 (C4 (Web Text))

Max Activating Token Index: 244