Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1890 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2671. Min Act: -0.0005

Data Index: 774937 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2661. Min Act: -0.0005

Data Index: 1003869 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2554. Min Act: -0.0005

Data Index: 436359 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2612. Min Act: -0.0005

Data Index: 645226 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2598. Min Act: -0.0005

Data Index: 970819 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2595. Min Act: -0.0005

Data Index: 437205 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2477. Min Act: -0.0005

Data Index: 964473 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2649. Min Act: -0.0005

Data Index: 1113623 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2479. Min Act: -0.0005

Data Index: 1174012 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2642. Min Act: -0.0005

Data Index: 579296 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2631. Min Act: -0.0005

Data Index: 745281 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2537. Min Act: -0.0005

Data Index: 526936 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2541. Min Act: -0.0005

Data Index: 1333941 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2547. Min Act: -0.0005

Data Index: 695101 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2453. Min Act: -0.0005

Data Index: 268793 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2545. Min Act: -0.0005

Data Index: 1272504 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2534. Min Act: -0.0005

Data Index: 547579 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2532. Min Act: -0.0005

Data Index: 1359113 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2523. Min Act: -0.0005

Data Index: 1045673 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2517. Min Act: -0.0005

Data Index: 1125657 (C4 (Web Text))

Max Activating Token Index: 25