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

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

Neuron 678 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0597. Min Act: -0.0001

Data Index: 703699 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0566. Min Act: -0.0001

Data Index: 551652 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1244913 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1258142 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0547. Min Act: -0.0001

Data Index: 372744 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0591. Min Act: -0.0001

Data Index: 384511 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0548. Min Act: -0.0001

Data Index: 559525 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0483. Min Act: -0.0001

Data Index: 1261802 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0519. Min Act: -0.0001

Data Index: 218192 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0522. Min Act: -0.0001

Data Index: 492330 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0537. Min Act: -0.0001

Data Index: 560569 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0524. Min Act: -0.0001

Data Index: 976630 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0459. Min Act: -0.0001

Data Index: 370643 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1104987 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0513. Min Act: -0.0001

Data Index: 1231987 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0552. Min Act: -0.0001

Data Index: 754370 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0499. Min Act: -0.0001

Data Index: 29060 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0522. Min Act: -0.0001

Data Index: 1004494 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0498. Min Act: -0.0001

Data Index: 530899 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0507. Min Act: -0.0001

Data Index: 191838 (C4 (Web Text))

Max Activating Token Index: 726