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

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

Neuron 5374 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: 0.0500. Min Range: -0.0500

Max Act: 0.0500. Min Act: -0.0002

Data Index: 753242 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1146563 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1334182 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0478. Min Act: -0.0002

Data Index: 142979 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0454. Min Act: -0.0002

Data Index: 952531 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1259837 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0461. Min Act: -0.0002

Data Index: 918094 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0435. Min Act: -0.0002

Data Index: 385679 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0438. Min Act: -0.0002

Data Index: 611591 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0434. Min Act: -0.0002

Data Index: 493478 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0441. Min Act: -0.0002

Data Index: 229252 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0431. Min Act: -0.0002

Data Index: 388335 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1199996 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0430. Min Act: -0.0002

Data Index: 986336 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0427. Min Act: -0.0002

Data Index: 356699 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0422. Min Act: -0.0002

Data Index: 946116 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1343784 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1198899 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1202671 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0409. Min Act: -0.0002

Data Index: 181405 (C4 (Web Text))

Max Activating Token Index: 646