Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2430 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.4401. Min Act: -0.0000

Data Index: 361773 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.3991. Min Act: -0.0000

Data Index: 460072 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.3257. Min Act: -0.0000

Data Index: 113820 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.3108. Min Act: -0.0000

Data Index: 97937 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.3186. Min Act: -0.0000

Data Index: 663743 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.3030. Min Act: -0.0000

Data Index: 467485 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2839. Min Act: -0.0000

Data Index: 190930 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2989. Min Act: -0.0000

Data Index: 428660 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2898. Min Act: -0.0000

Data Index: 326268 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2896. Min Act: -0.0000

Data Index: 169917 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1210499 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2889. Min Act: -0.0000

Data Index: 496690 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2803. Min Act: -0.0000

Data Index: 957185 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2713. Min Act: -0.0000

Data Index: 468773 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2696. Min Act: -0.0000

Data Index: 974215 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1072163 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2826. Min Act: -0.0000

Data Index: 86191 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2619. Min Act: -0.0000

Data Index: 1056563 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2630. Min Act: -0.0000

Data Index: 123911 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2686. Min Act: -0.0000

Data Index: 140258 (C4 (Web Text))

Max Activating Token Index: 915