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

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

Neuron 2026 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7167. Min Range: -1.7167

Max Act: 1.7167. Min Act: -0.0001

Data Index: 472819 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 1.7167. Min Range: -1.7167

Max Act: 1.6044. Min Act: -0.0001

Data Index: 647909 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 1.7167. Min Range: -1.7167

Max Act: 1.6816. Min Act: -0.0001

Data Index: 913568 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 1.7167. Min Range: -1.7167

Max Act: 1.6995. Min Act: -0.0001

Data Index: 802789 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 1.7167. Min Range: -1.7167

Max Act: 1.4129. Min Act: -0.0001

Data Index: 176409 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 1.7167. Min Range: -1.7167

Max Act: 1.3210. Min Act: -0.0001

Data Index: 223666 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 1.7167. Min Range: -1.7167

Max Act: 1.3738. Min Act: -0.0001

Data Index: 969084 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 1.7167. Min Range: -1.7167

Max Act: 1.3374. Min Act: -0.0001

Data Index: 1325597 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 1.7167. Min Range: -1.7167

Max Act: 1.4362. Min Act: -0.0001

Data Index: 569714 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 1.7167. Min Range: -1.7167

Max Act: 1.6033. Min Act: -0.0001

Data Index: 169011 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 1.7167. Min Range: -1.7167

Max Act: 1.4991. Min Act: -0.0001

Data Index: 1111900 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 1.7167. Min Range: -1.7167

Max Act: 1.3182. Min Act: -0.0001

Data Index: 313093 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 1.7167. Min Range: -1.7167

Max Act: 1.3568. Min Act: -0.0001

Data Index: 640592 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 1.7167. Min Range: -1.7167

Max Act: 1.2811. Min Act: -0.0001

Data Index: 494383 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 1.7167. Min Range: -1.7167

Max Act: 1.3370. Min Act: -0.0001

Data Index: 990639 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 1.7167. Min Range: -1.7167

Max Act: 1.3234. Min Act: -0.0001

Data Index: 397731 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 1.7167. Min Range: -1.7167

Max Act: 1.3871. Min Act: -0.0001

Data Index: 661063 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 1.7167. Min Range: -1.7167

Max Act: 1.3277. Min Act: -0.0001

Data Index: 348549 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 1.7167. Min Range: -1.7167

Max Act: 1.2287. Min Act: -0.0001

Data Index: 261237 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 1.7167. Min Range: -1.7167

Max Act: 1.2583. Min Act: -0.0001

Data Index: 315019 (C4 (Web Text))

Max Activating Token Index: 852