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

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

Neuron 4324 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: 1.6670. Min Range: -1.6670

Max Act: 1.5122. Min Act: -0.0001

Data Index: 400595 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.6670. Min Act: -0.0001

Data Index: 858188 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.6665. Min Act: -0.0001

Data Index: 439376 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.4688. Min Act: -0.0001

Data Index: 1158255 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.4330. Min Act: -0.0001

Data Index: 454562 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.5402. Min Act: -0.0001

Data Index: 899936 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.5242. Min Act: -0.0001

Data Index: 291059 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.5058. Min Act: -0.0001

Data Index: 853221 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.5114. Min Act: -0.0001

Data Index: 1277310 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.4492. Min Act: -0.0001

Data Index: 1221583 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.5421. Min Act: -0.0001

Data Index: 351752 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.4485. Min Act: -0.0001

Data Index: 1300153 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.4822. Min Act: -0.0001

Data Index: 863502 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.3985. Min Act: -0.0001

Data Index: 104365 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.3845. Min Act: -0.0001

Data Index: 774225 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.3767. Min Act: -0.0001

Data Index: 716885 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.4543. Min Act: -0.0001

Data Index: 1235217 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.4355. Min Act: -0.0001

Data Index: 727436 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.4326. Min Act: -0.0001

Data Index: 16704 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.3862. Min Act: -0.0001

Data Index: 1251918 (C4 (Web Text))

Max Activating Token Index: 690