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

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

Neuron 2032 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: 0.0548. Min Range: -0.0548

Max Act: 0.0548. Min Act: -0.0005

Data Index: 682576 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0526. Min Act: -0.0005

Data Index: 329058 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0459. Min Act: -0.0005

Data Index: 1243491 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0500. Min Act: -0.0005

Data Index: 825827 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0475. Min Act: -0.0005

Data Index: 310882 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0490. Min Act: -0.0005

Data Index: 788113 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0463. Min Act: -0.0005

Data Index: 472881 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0486. Min Act: -0.0005

Data Index: 886902 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0461. Min Act: -0.0005

Data Index: 779793 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0457. Min Act: -0.0005

Data Index: 489188 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0476. Min Act: -0.0005

Data Index: 124503 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0475. Min Act: -0.0005

Data Index: 592693 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0458. Min Act: -0.0005

Data Index: 896069 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0465. Min Act: -0.0005

Data Index: 1110575 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0447. Min Act: -0.0005

Data Index: 1159504 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0463. Min Act: -0.0005

Data Index: 1356689 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0479. Min Act: -0.0005

Data Index: 458032 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0435. Min Act: -0.0005

Data Index: 1111741 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0444. Min Act: -0.0005

Data Index: 309128 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0440. Min Act: -0.0005

Data Index: 1198508 (C4 (Web Text))

Max Activating Token Index: 982