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

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

Neuron 2380 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: 0.5127. Min Range: -0.5127

Max Act: 0.4558. Min Act: -0.0000

Data Index: 56206 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1072114 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1093997 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.4056. Min Act: -0.0000

Data Index: 418181 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3506. Min Act: -0.0000

Data Index: 1351784 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3549. Min Act: -0.0000

Data Index: 4778 (C4 (Web Text))

Max Activating Token Index: 791

Text #6

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3400. Min Act: -0.0000

Data Index: 595421 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3225. Min Act: -0.0000

Data Index: 1134839 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3162. Min Act: -0.0000

Data Index: 401173 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3227. Min Act: -0.0000

Data Index: 201344 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3125. Min Act: -0.0000

Data Index: 546942 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3197. Min Act: -0.0000

Data Index: 860436 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.2987. Min Act: -0.0000

Data Index: 933032 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3144. Min Act: -0.0000

Data Index: 572917 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3174. Min Act: -0.0000

Data Index: 943213 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1274101 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1319795 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.2795. Min Act: -0.0000

Data Index: 305741 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3208. Min Act: -0.0000

Data Index: 134793 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.5127. Min Range: -0.5127

Max Act: 0.3054. Min Act: -0.0000

Data Index: 1052267 (C4 (Web Text))

Max Activating Token Index: 248