Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3433 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.2517. Min Act: -0.0000

Data Index: 356789 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.4202. Min Act: -0.0000

Data Index: 881987 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.0933. Min Act: -0.0000

Data Index: 974644 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 3.4202. Min Range: -3.4202

Max Act: 2.8122. Min Act: -0.0000

Data Index: 317551 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 3.4202. Min Range: -3.4202

Max Act: 2.9024. Min Act: -0.0000

Data Index: 619797 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 3.4202. Min Range: -3.4202

Max Act: 2.7114. Min Act: -0.0000

Data Index: 1433814 (Python Code)

Max Activating Token Index: 259

Text #6

Max Range: 3.4202. Min Range: -3.4202

Max Act: 2.8452. Min Act: -0.0000

Data Index: 1102787 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 3.4202. Min Range: -3.4202

Max Act: 2.7002. Min Act: -0.0000

Data Index: 18182 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 3.4202. Min Range: -3.4202

Max Act: 2.6960. Min Act: -0.0000

Data Index: 375680 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 3.4202. Min Range: -3.4202

Max Act: 2.5792. Min Act: -0.0000

Data Index: 1482625 (Python Code)

Max Activating Token Index: 93

Text #10

Max Range: 3.4202. Min Range: -3.4202

Max Act: 2.5351. Min Act: -0.0000

Data Index: 657651 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 3.4202. Min Range: -3.4202

Max Act: 2.4184. Min Act: -0.0000

Data Index: 717747 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 3.4202. Min Range: -3.4202

Max Act: 2.4836. Min Act: -0.0000

Data Index: 27908 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.4202. Min Range: -3.4202

Max Act: 2.4766. Min Act: -0.0000

Data Index: 345165 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 3.4202. Min Range: -3.4202

Max Act: 2.4621. Min Act: -0.0000

Data Index: 239746 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 3.4202. Min Range: -3.4202

Max Act: 2.3237. Min Act: -0.0000

Data Index: 952194 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 3.4202. Min Range: -3.4202

Max Act: 2.4210. Min Act: -0.0000

Data Index: 850460 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 3.4202. Min Range: -3.4202

Max Act: 2.3709. Min Act: -0.0000

Data Index: 105525 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 3.4202. Min Range: -3.4202

Max Act: 2.3523. Min Act: -0.0000

Data Index: 79415 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 3.4202. Min Range: -3.4202

Max Act: 2.2320. Min Act: -0.0000

Data Index: 45661 (C4 (Web Text))

Max Activating Token Index: 247