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

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

Neuron 1263 in Layer 0

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: 0.8273. Min Range: -0.8273

Max Act: 0.8273. Min Act: -0.0001

Data Index: 100781 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.8194. Min Act: -0.0001

Data Index: 28655 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.7921. Min Act: -0.0001

Data Index: 601228 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.7843. Min Act: -0.0001

Data Index: 168022 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.7870. Min Act: -0.0001

Data Index: 426698 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.7789. Min Act: -0.0001

Data Index: 285725 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.7948. Min Act: -0.0001

Data Index: 298999 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.7830. Min Act: -0.0001

Data Index: 10187 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.7657. Min Act: -0.0001

Data Index: 99953 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.7761. Min Act: -0.0001

Data Index: 324352 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.7648. Min Act: -0.0001

Data Index: 801810 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.7632. Min Act: -0.0001

Data Index: 566939 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.7649. Min Act: -0.0001

Data Index: 635876 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.7463. Min Act: -0.0001

Data Index: 237002 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.7537. Min Act: -0.0001

Data Index: 115100 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.7592. Min Act: -0.0002

Data Index: 516970 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.7617. Min Act: -0.0001

Data Index: 492206 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.7481. Min Act: -0.0001

Data Index: 1356962 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.7516. Min Act: -0.0001

Data Index: 298567 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.7448. Min Act: -0.0001

Data Index: 333282 (C4 (Web Text))

Max Activating Token Index: 622