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

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

Neuron 5300 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2135. Min Range: -1.2135

Max Act: 1.1823. Min Act: -0.0000

Data Index: 586618 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 1.2135. Min Range: -1.2135

Max Act: 1.2135. Min Act: -0.0000

Data Index: 1177563 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 1.2135. Min Range: -1.2135

Max Act: 1.0722. Min Act: -0.0000

Data Index: 1249043 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 1.2135. Min Range: -1.2135

Max Act: 1.2053. Min Act: -0.0000

Data Index: 1203853 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 1.2135. Min Range: -1.2135

Max Act: 1.2006. Min Act: -0.0000

Data Index: 727727 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 1.2135. Min Range: -1.2135

Max Act: 1.1551. Min Act: -0.0000

Data Index: 1029199 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 1.2135. Min Range: -1.2135

Max Act: 1.0849. Min Act: -0.0000

Data Index: 997380 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 1.2135. Min Range: -1.2135

Max Act: 1.0690. Min Act: -0.0000

Data Index: 1024757 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 1.2135. Min Range: -1.2135

Max Act: 1.0654. Min Act: -0.0000

Data Index: 990603 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.9427. Min Act: -0.0000

Data Index: 1189472 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 1.2135. Min Range: -1.2135

Max Act: 1.0563. Min Act: -0.0000

Data Index: 555262 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 1.2135. Min Range: -1.2135

Max Act: 1.0159. Min Act: -0.0000

Data Index: 226636 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.9839. Min Act: -0.0000

Data Index: 1301213 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.9811. Min Act: -0.0000

Data Index: 1068618 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.9971. Min Act: -0.0000

Data Index: 788065 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.9381. Min Act: -0.0000

Data Index: 959273 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.9945. Min Act: -0.0000

Data Index: 972329 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.9654. Min Act: -0.0000

Data Index: 23424 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.9912. Min Act: -0.0000

Data Index: 1014189 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.2135. Min Range: -1.2135

Max Act: 0.9863. Min Act: -0.0000

Data Index: 20335 (C4 (Web Text))

Max Activating Token Index: 62