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

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

Neuron 544 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0595. Min Act: -0.0003

Data Index: 783549 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0513. Min Act: -0.0003

Data Index: 516542 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0508. Min Act: -0.0003

Data Index: 427115 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0481. Min Act: -0.0003

Data Index: 482521 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0513. Min Act: -0.0003

Data Index: 1321592 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0507. Min Act: -0.0003

Data Index: 443271 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0477. Min Act: -0.0003

Data Index: 828919 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1067729 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0461. Min Act: -0.0003

Data Index: 77400 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0476. Min Act: -0.0003

Data Index: 790925 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0486. Min Act: -0.0003

Data Index: 402366 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0458. Min Act: -0.0003

Data Index: 1108310 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0426. Min Act: -0.0003

Data Index: 273052 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0464. Min Act: -0.0003

Data Index: 173599 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0448. Min Act: -0.0003

Data Index: 243340 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0461. Min Act: -0.0003

Data Index: 623380 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0435. Min Act: -0.0003

Data Index: 715985 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0486. Min Act: -0.0003

Data Index: 1176808 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0431. Min Act: -0.0003

Data Index: 195702 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0414. Min Act: -0.0003

Data Index: 867415 (C4 (Web Text))

Max Activating Token Index: 97