Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2184 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 5.1955. Min Range: -5.1955

Max Act: 4.8258. Min Act: -0.0003

Data Index: 8812 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 5.1955. Min Range: -5.1955

Max Act: 4.8811. Min Act: -0.0003

Data Index: 1159707 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 5.1955. Min Range: -5.1955

Max Act: 5.1955. Min Act: -0.0003

Data Index: 373394 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 5.1955. Min Range: -5.1955

Max Act: 4.8280. Min Act: -0.0003

Data Index: 354223 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 5.1955. Min Range: -5.1955

Max Act: 4.5567. Min Act: -0.0003

Data Index: 94179 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 5.1955. Min Range: -5.1955

Max Act: 4.7471. Min Act: -0.0003

Data Index: 766903 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 5.1955. Min Range: -5.1955

Max Act: 4.2667. Min Act: -0.0003

Data Index: 1331095 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 5.1955. Min Range: -5.1955

Max Act: 4.8652. Min Act: -0.0003

Data Index: 1287518 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 5.1955. Min Range: -5.1955

Max Act: 4.9047. Min Act: -0.0003

Data Index: 277425 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 5.1955. Min Range: -5.1955

Max Act: 5.0097. Min Act: -0.0003

Data Index: 1067807 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 5.1955. Min Range: -5.1955

Max Act: 4.3933. Min Act: -0.0003

Data Index: 987423 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 5.1955. Min Range: -5.1955

Max Act: 4.5432. Min Act: -0.0003

Data Index: 1062835 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 5.1955. Min Range: -5.1955

Max Act: 4.6652. Min Act: -0.0003

Data Index: 874887 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 5.1955. Min Range: -5.1955

Max Act: 3.9219. Min Act: -0.0003

Data Index: 1045899 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 5.1955. Min Range: -5.1955

Max Act: 4.2276. Min Act: -0.0003

Data Index: 341511 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 5.1955. Min Range: -5.1955

Max Act: 4.1923. Min Act: -0.0003

Data Index: 1336543 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 5.1955. Min Range: -5.1955

Max Act: 4.6234. Min Act: -0.0003

Data Index: 1151094 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 5.1955. Min Range: -5.1955

Max Act: 4.3079. Min Act: -0.0003

Data Index: 896506 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 5.1955. Min Range: -5.1955

Max Act: 4.5857. Min Act: -0.0003

Data Index: 1163702 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 5.1955. Min Range: -5.1955

Max Act: 4.0883. Min Act: -0.0003

Data Index: 2660 (C4 (Web Text))

Max Activating Token Index: 788