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

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

Neuron 505 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: 0.0467. Min Range: -0.0467

Max Act: 0.0467. Min Act: -0.0002

Data Index: 856792 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0451. Min Act: -0.0001

Data Index: 508222 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1488167 (Python Code)

Max Activating Token Index: 721

Text #3

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1242007 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0428. Min Act: -0.0001

Data Index: 1071274 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0412. Min Act: -0.0001

Data Index: 970869 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0417. Min Act: -0.0001

Data Index: 785770 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1554269 (Python Code)

Max Activating Token Index: 962

Text #8

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0413. Min Act: -0.0001

Data Index: 498130 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0413. Min Act: -0.0001

Data Index: 636868 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0406. Min Act: -0.0001

Data Index: 56256 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0401. Min Act: -0.0001

Data Index: 14088 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1226679 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0399. Min Act: -0.0001

Data Index: 876461 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0401. Min Act: -0.0001

Data Index: 1150045 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0400. Min Act: -0.0001

Data Index: 210818 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1365843 (Python Code)

Max Activating Token Index: 725

Text #17

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0396. Min Act: -0.0001

Data Index: 845778 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0389. Min Act: -0.0002

Data Index: 650151 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0390. Min Act: -0.0001

Data Index: 1209280 (C4 (Web Text))

Max Activating Token Index: 613