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

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

Neuron 759 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: 0.4923. Min Range: -0.4923

Max Act: 0.4923. Min Act: -0.0002

Data Index: 1054210 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.4105. Min Act: -0.0002

Data Index: 217919 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3877. Min Act: -0.0002

Data Index: 1165807 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3807. Min Act: -0.0002

Data Index: 182997 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3731. Min Act: -0.0002

Data Index: 495 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3815. Min Act: -0.0003

Data Index: 335057 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3779. Min Act: -0.0002

Data Index: 469061 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3632. Min Act: -0.0002

Data Index: 289832 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3660. Min Act: -0.0003

Data Index: 547533 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3620. Min Act: -0.0002

Data Index: 795603 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3455. Min Act: -0.0002

Data Index: 1118470 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3550. Min Act: -0.0002

Data Index: 820171 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3470. Min Act: -0.0002

Data Index: 1339058 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3515. Min Act: -0.0002

Data Index: 601794 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3406. Min Act: -0.0002

Data Index: 138931 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3316. Min Act: -0.0002

Data Index: 80734 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3298. Min Act: -0.0002

Data Index: 1249041 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3459. Min Act: -0.0002

Data Index: 304110 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3355. Min Act: -0.0002

Data Index: 1105045 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.4923. Min Range: -0.4923

Max Act: 0.3348. Min Act: -0.0002

Data Index: 839232 (C4 (Web Text))

Max Activating Token Index: 944