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

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

Neuron 1041 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.5164. Min Act: -0.0000

Data Index: 746780 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4632. Min Act: -0.0000

Data Index: 509355 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4899. Min Act: -0.0001

Data Index: 242405 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4744. Min Act: -0.0000

Data Index: 66680 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4409. Min Act: -0.0000

Data Index: 708923 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4377. Min Act: -0.0000

Data Index: 238305 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1337256 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4271. Min Act: -0.0000

Data Index: 376756 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4241. Min Act: -0.0000

Data Index: 491096 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4948. Min Act: -0.0000

Data Index: 361622 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4444. Min Act: -0.0001

Data Index: 485603 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1346262 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4018. Min Act: -0.0000

Data Index: 539039 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3983. Min Act: -0.0000

Data Index: 1221119 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4095. Min Act: -0.0000

Data Index: 229073 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4045. Min Act: -0.0000

Data Index: 569916 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3952. Min Act: -0.0000

Data Index: 310104 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4010. Min Act: -0.0001

Data Index: 54224 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4105. Min Act: -0.0000

Data Index: 1225240 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4002. Min Act: -0.0000

Data Index: 704605 (C4 (Web Text))

Max Activating Token Index: 262