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

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

Neuron 3694 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5449. Min Range: -7.5449

Max Act: 7.5449. Min Act: 0.0000

Data Index: 1150107 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 7.5449. Min Range: -7.5449

Max Act: 5.7765. Min Act: -0.0000

Data Index: 164771 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 7.5449. Min Range: -7.5449

Max Act: 5.3473. Min Act: -0.0000

Data Index: 1126076 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 7.5449. Min Range: -7.5449

Max Act: 5.0480. Min Act: -0.0000

Data Index: 172695 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 7.5449. Min Range: -7.5449

Max Act: 4.7080. Min Act: -0.0000

Data Index: 1199749 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 7.5449. Min Range: -7.5449

Max Act: 4.6931. Min Act: -0.0000

Data Index: 1264858 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 7.5449. Min Range: -7.5449

Max Act: 4.4112. Min Act: -0.0000

Data Index: 797705 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 7.5449. Min Range: -7.5449

Max Act: 4.4430. Min Act: -0.0000

Data Index: 141466 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 7.5449. Min Range: -7.5449

Max Act: 4.2433. Min Act: -0.0000

Data Index: 204620 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 7.5449. Min Range: -7.5449

Max Act: 4.2528. Min Act: -0.0000

Data Index: 329004 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 7.5449. Min Range: -7.5449

Max Act: 3.9009. Min Act: -0.0000

Data Index: 399150 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 7.5449. Min Range: -7.5449

Max Act: 4.2641. Min Act: -0.0000

Data Index: 1186144 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 7.5449. Min Range: -7.5449

Max Act: 3.6901. Min Act: -0.0000

Data Index: 3028 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 7.5449. Min Range: -7.5449

Max Act: 3.7354. Min Act: -0.0000

Data Index: 352744 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 7.5449. Min Range: -7.5449

Max Act: 4.0820. Min Act: -0.0000

Data Index: 1063836 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 7.5449. Min Range: -7.5449

Max Act: 3.2520. Min Act: -0.0000

Data Index: 1203924 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 7.5449. Min Range: -7.5449

Max Act: 2.6898. Min Act: -0.0000

Data Index: 1239138 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 7.5449. Min Range: -7.5449

Max Act: 1.9738. Min Act: -0.0000

Data Index: 1147434 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 7.5449. Min Range: -7.5449

Max Act: 1.8536. Min Act: -0.0000

Data Index: 774227 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 7.5449. Min Range: -7.5449

Max Act: 1.8039. Min Act: -0.0000

Data Index: 494643 (C4 (Web Text))

Max Activating Token Index: 801