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

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

Neuron 1625 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3081. Min Range: -2.3081

Max Act: 2.3081. Min Act: -0.0002

Data Index: 696952 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 2.3081. Min Range: -2.3081

Max Act: 2.2820. Min Act: 0.0001

Data Index: 592820 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 2.3081. Min Range: -2.3081

Max Act: 2.0918. Min Act: -0.0002

Data Index: 262461 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 2.3081. Min Range: -2.3081

Max Act: 2.1190. Min Act: -0.0002

Data Index: 822136 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 2.3081. Min Range: -2.3081

Max Act: 1.9434. Min Act: 0.0001

Data Index: 328368 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 2.3081. Min Range: -2.3081

Max Act: 1.9915. Min Act: -0.0002

Data Index: 1187470 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 2.3081. Min Range: -2.3081

Max Act: 1.9289. Min Act: -0.0002

Data Index: 1354984 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 2.3081. Min Range: -2.3081

Max Act: 1.8493. Min Act: -0.0002

Data Index: 115255 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 2.3081. Min Range: -2.3081

Max Act: 1.9432. Min Act: -0.0002

Data Index: 1087078 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 2.3081. Min Range: -2.3081

Max Act: 1.8854. Min Act: -0.0002

Data Index: 1187708 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 2.3081. Min Range: -2.3081

Max Act: 1.8423. Min Act: -0.0002

Data Index: 320064 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 2.3081. Min Range: -2.3081

Max Act: 1.8199. Min Act: -0.0002

Data Index: 995859 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 2.3081. Min Range: -2.3081

Max Act: 1.8559. Min Act: -0.0002

Data Index: 714424 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 2.3081. Min Range: -2.3081

Max Act: 1.8621. Min Act: -0.0002

Data Index: 11683 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 2.3081. Min Range: -2.3081

Max Act: 1.8117. Min Act: -0.0002

Data Index: 628241 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 2.3081. Min Range: -2.3081

Max Act: 1.8448. Min Act: -0.0002

Data Index: 911764 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 2.3081. Min Range: -2.3081

Max Act: 1.7835. Min Act: -0.0002

Data Index: 269085 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 2.3081. Min Range: -2.3081

Max Act: 1.7776. Min Act: -0.0002

Data Index: 611366 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 2.3081. Min Range: -2.3081

Max Act: 1.8178. Min Act: -0.0002

Data Index: 180417 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 2.3081. Min Range: -2.3081

Max Act: 1.8523. Min Act: -0.0001

Data Index: 678284 (C4 (Web Text))

Max Activating Token Index: 53