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

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

Neuron 3155 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1063021 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0685. Min Act: -0.0000

Data Index: 1086534 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0659. Min Act: -0.0001

Data Index: 761584 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0637. Min Act: -0.0001

Data Index: 455138 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0642. Min Act: -0.0001

Data Index: 1139343 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1332142 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1189986 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0563. Min Act: -0.0001

Data Index: 998678 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0527. Min Act: -0.0001

Data Index: 854798 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0533. Min Act: -0.0001

Data Index: 633243 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0548. Min Act: -0.0001

Data Index: 571216 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0523. Min Act: -0.0001

Data Index: 394235 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0521. Min Act: -0.0001

Data Index: 757277 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0560. Min Act: -0.0001

Data Index: 753987 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0498. Min Act: -0.0001

Data Index: 792576 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0508. Min Act: -0.0001

Data Index: 366399 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0487. Min Act: -0.0001

Data Index: 753334 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0485. Min Act: -0.0001

Data Index: 435726 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0517. Min Act: -0.0001

Data Index: 636234 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0514. Min Act: -0.0001

Data Index: 815442 (C4 (Web Text))

Max Activating Token Index: 655