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

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

Neuron 1795 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0734. Min Act: -0.0002

Data Index: 527273 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0661. Min Act: -0.0002

Data Index: 723668 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1477002 (Python Code)

Max Activating Token Index: 122

Text #3

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1142948 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1314766 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0605. Min Act: -0.0002

Data Index: 607716 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1539644 (Python Code)

Max Activating Token Index: 94

Text #7

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0593. Min Act: -0.0002

Data Index: 860185 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1203300 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0589. Min Act: -0.0002

Data Index: 186214 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0588. Min Act: -0.0002

Data Index: 633991 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0579. Min Act: -0.0002

Data Index: 439096 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1229875 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0582. Min Act: -0.0002

Data Index: 542117 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1202936 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0540. Min Act: -0.0002

Data Index: 171495 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0557. Min Act: -0.0002

Data Index: 309221 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0550. Min Act: -0.0002

Data Index: 582599 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0533. Min Act: -0.0002

Data Index: 552257 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1265527 (C4 (Web Text))

Max Activating Token Index: 119