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

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

Neuron 1935 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: 0.4249. Min Range: -0.4249

Max Act: 0.4249. Min Act: -0.0000

Data Index: 197428 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3938. Min Act: -0.0000

Data Index: 678241 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3745. Min Act: -0.0000

Data Index: 782479 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3584. Min Act: -0.0000

Data Index: 224790 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3393. Min Act: -0.0000

Data Index: 937869 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3382. Min Act: -0.0000

Data Index: 665756 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3347. Min Act: -0.0000

Data Index: 553360 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3332. Min Act: -0.0000

Data Index: 975561 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3327. Min Act: -0.0000

Data Index: 497584 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3253. Min Act: -0.0000

Data Index: 47154 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3286. Min Act: -0.0000

Data Index: 828099 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3375. Min Act: -0.0000

Data Index: 981381 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3371. Min Act: 0.0000

Data Index: 1008216 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3173. Min Act: -0.0000

Data Index: 1333381 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1017992 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3173. Min Act: -0.0000

Data Index: 179488 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3046. Min Act: -0.0000

Data Index: 63394 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3048. Min Act: 0.0000

Data Index: 225932 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.2900. Min Act: -0.0000

Data Index: 830565 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3041. Min Act: -0.0000

Data Index: 777109 (C4 (Web Text))

Max Activating Token Index: 795