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

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

Neuron 3927 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1047542 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0659. Min Act: -0.0001

Data Index: 829389 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0646. Min Act: -0.0001

Data Index: 538948 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0659. Min Act: -0.0001

Data Index: 87229 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1216086 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0599. Min Act: -0.0001

Data Index: 1158433 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0564. Min Act: -0.0001

Data Index: 249040 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0595. Min Act: -0.0001

Data Index: 212052 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0547. Min Act: -0.0001

Data Index: 1349696 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0533. Min Act: -0.0001

Data Index: 586915 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0549. Min Act: -0.0001

Data Index: 707691 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0576. Min Act: -0.0001

Data Index: 796131 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0597. Min Act: -0.0001

Data Index: 636179 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0512. Min Act: -0.0001

Data Index: 1622213 (Python Code)

Max Activating Token Index: 927

Text #14

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0551. Min Act: -0.0001

Data Index: 513660 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0500. Min Act: -0.0001

Data Index: 407544 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0520. Min Act: -0.0001

Data Index: 120186 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1227838 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0540. Min Act: -0.0001

Data Index: 185420 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0530. Min Act: -0.0001

Data Index: 425096 (C4 (Web Text))

Max Activating Token Index: 228