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

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

Neuron 761 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.2887. Min Act: -0.0000

Data Index: 1181498 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.2835. Min Act: -0.0000

Data Index: 880070 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.2700. Min Act: -0.0000

Data Index: 313897 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.2512. Min Act: -0.0000

Data Index: 177795 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.3005. Min Act: -0.0000

Data Index: 172240 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1410. Min Act: -0.0000

Data Index: 526179 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1378. Min Act: -0.0000

Data Index: 767067 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.0225. Min Act: -0.0000

Data Index: 130005 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.0290. Min Act: 0.0001

Data Index: 739936 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.0925. Min Act: -0.0000

Data Index: 868661 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.0035. Min Act: -0.0000

Data Index: 479941 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.0321. Min Act: -0.0000

Data Index: 461261 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.9616. Min Act: -0.0000

Data Index: 331360 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.9305. Min Act: -0.0000

Data Index: 774278 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.9251. Min Act: -0.0000

Data Index: 152718 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.9313. Min Act: -0.0000

Data Index: 1203153 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.9171. Min Act: -0.0000

Data Index: 1110955 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.9680. Min Act: -0.0000

Data Index: 1162970 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.8957. Min Act: 0.0000

Data Index: 772354 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.8801. Min Act: -0.0000

Data Index: 330790 (C4 (Web Text))

Max Activating Token Index: 537