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

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

Neuron 1040 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: 0.6629. Min Range: -0.6629

Max Act: 0.6629. Min Act: -0.0000

Data Index: 1319079 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1017610 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4318. Min Act: -0.0000

Data Index: 477462 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.3939. Min Act: 0.0000

Data Index: 988197 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.3976. Min Act: -0.0000

Data Index: 233480 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.3318. Min Act: -0.0000

Data Index: 153000 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.3224. Min Act: 0.0000

Data Index: 966588 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.3281. Min Act: -0.0000

Data Index: 729475 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.3166. Min Act: -0.0000

Data Index: 1219209 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.3228. Min Act: -0.0000

Data Index: 701190 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1181804 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.3056. Min Act: -0.0000

Data Index: 511815 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.3036. Min Act: -0.0000

Data Index: 936682 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.3021. Min Act: -0.0000

Data Index: 989651 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.3224. Min Act: -0.0000

Data Index: 894281 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.2760. Min Act: -0.0000

Data Index: 438087 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1030384 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.2988. Min Act: -0.0000

Data Index: 276510 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.2732. Min Act: -0.0000

Data Index: 423389 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.2830. Min Act: -0.0000

Data Index: 330286 (C4 (Web Text))

Max Activating Token Index: 811