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

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

Neuron 2982 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4079. Min Range: -0.4079

Max Act: 0.3902. Min Act: -0.0000

Data Index: 1346628 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.4079. Min Range: -0.4079

Max Act: 0.4079. Min Act: -0.0000

Data Index: 212619 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.4079. Min Range: -0.4079

Max Act: 0.3348. Min Act: -0.0000

Data Index: 749111 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.4079. Min Range: -0.4079

Max Act: 0.3487. Min Act: -0.0000

Data Index: 461520 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 0.4079. Min Range: -0.4079

Max Act: 0.3310. Min Act: -0.0000

Data Index: 1460764 (Python Code)

Max Activating Token Index: 570

Text #5

Max Range: 0.4079. Min Range: -0.4079

Max Act: 0.3241. Min Act: -0.0000

Data Index: 997064 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.4079. Min Range: -0.4079

Max Act: 0.3152. Min Act: -0.0000

Data Index: 515361 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.4079. Min Range: -0.4079

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1271626 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.4079. Min Range: -0.4079

Max Act: 0.2950. Min Act: -0.0000

Data Index: 1336798 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.4079. Min Range: -0.4079

Max Act: 0.3250. Min Act: -0.0000

Data Index: 800944 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.4079. Min Range: -0.4079

Max Act: 0.3110. Min Act: -0.0000

Data Index: 874012 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.4079. Min Range: -0.4079

Max Act: 0.3096. Min Act: -0.0000

Data Index: 360105 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.4079. Min Range: -0.4079

Max Act: 0.3115. Min Act: -0.0000

Data Index: 372806 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.4079. Min Range: -0.4079

Max Act: 0.2979. Min Act: -0.0000

Data Index: 580596 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.4079. Min Range: -0.4079

Max Act: 0.3157. Min Act: -0.0000

Data Index: 770285 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 0.4079. Min Range: -0.4079

Max Act: 0.3011. Min Act: -0.0000

Data Index: 1101444 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.4079. Min Range: -0.4079

Max Act: 0.3019. Min Act: -0.0000

Data Index: 852070 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.4079. Min Range: -0.4079

Max Act: 0.2996. Min Act: -0.0000

Data Index: 473625 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.4079. Min Range: -0.4079

Max Act: 0.3007. Min Act: -0.0000

Data Index: 778939 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.4079. Min Range: -0.4079

Max Act: 0.2995. Min Act: -0.0000

Data Index: 580244 (C4 (Web Text))

Max Activating Token Index: 791