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

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

Neuron 5303 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.8359. Min Act: -0.0000

Data Index: 135923 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.7300. Min Act: -0.0000

Data Index: 184380 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.6553. Min Act: -0.0000

Data Index: 846319 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.7098. Min Act: -0.0000

Data Index: 1054152 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.6017. Min Act: -0.0000

Data Index: 324608 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.5835. Min Act: -0.0000

Data Index: 442889 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.5832. Min Act: -0.0000

Data Index: 895069 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.5642. Min Act: -0.0000

Data Index: 378157 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.6452. Min Act: -0.0000

Data Index: 270435 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.6150. Min Act: -0.0000

Data Index: 1212916 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.6277. Min Act: -0.0000

Data Index: 543075 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.5216. Min Act: -0.0000

Data Index: 271952 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.5780. Min Act: -0.0000

Data Index: 375229 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.5645. Min Act: -0.0000

Data Index: 1266681 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.4539. Min Act: -0.0000

Data Index: 763870 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.4498. Min Act: -0.0000

Data Index: 258715 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.4316. Min Act: -0.0000

Data Index: 44452 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.5121. Min Act: -0.0000

Data Index: 624558 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.4975. Min Act: -0.0000

Data Index: 1227570 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.4601. Min Act: -0.0000

Data Index: 263007 (C4 (Web Text))

Max Activating Token Index: 10