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

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

Neuron 539 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3825. Min Act: -0.0000

Data Index: 854408 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.4174. Min Act: -0.0000

Data Index: 495362 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3873. Min Act: -0.0000

Data Index: 810043 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1260993 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1067706 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3215. Min Act: -0.0000

Data Index: 1153737 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3162. Min Act: -0.0000

Data Index: 697126 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2993. Min Act: -0.0000

Data Index: 749102 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2913. Min Act: -0.0000

Data Index: 722761 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2627. Min Act: -0.0000

Data Index: 245028 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2462. Min Act: -0.0000

Data Index: 109311 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2291. Min Act: -0.0000

Data Index: 142595 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2632. Min Act: -0.0000

Data Index: 675044 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1027787 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2763. Min Act: -0.0000

Data Index: 729804 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1050133 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2817. Min Act: -0.0000

Data Index: 903692 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2564. Min Act: -0.0000

Data Index: 153844 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2830. Min Act: -0.0000

Data Index: 122165 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2901. Min Act: -0.0000

Data Index: 296057 (C4 (Web Text))

Max Activating Token Index: 432