Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1987 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6731. Min Act: -0.0000

Data Index: 785308 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6103. Min Act: -0.0000

Data Index: 705149 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6955. Min Act: -0.0000

Data Index: 443865 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6009. Min Act: -0.0000

Data Index: 533902 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5802. Min Act: -0.0000

Data Index: 1335737 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1341114 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5972. Min Act: -0.0000

Data Index: 268205 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5422. Min Act: -0.0000

Data Index: 216391 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5256. Min Act: -0.0000

Data Index: 1167626 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4951. Min Act: -0.0000

Data Index: 473528 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5336. Min Act: -0.0000

Data Index: 1015642 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1655730 (Python Code)

Max Activating Token Index: 557

Text #12

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5551. Min Act: -0.0000

Data Index: 269985 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5205. Min Act: -0.0000

Data Index: 608766 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5357. Min Act: -0.0000

Data Index: 931319 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5182. Min Act: -0.0000

Data Index: 734311 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5154. Min Act: -0.0000

Data Index: 462244 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4788. Min Act: -0.0000

Data Index: 296916 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5136. Min Act: -0.0000

Data Index: 1042078 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1028649 (C4 (Web Text))

Max Activating Token Index: 757