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

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

Neuron 3976 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1379. Min Act: -0.0000

Data Index: 1145404 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1248. Min Act: -0.0000

Data Index: 829369 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1203. Min Act: -0.0000

Data Index: 71367 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1133. Min Act: -0.0000

Data Index: 773805 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1202. Min Act: -0.0000

Data Index: 973558 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1205461 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1051. Min Act: -0.0000

Data Index: 80674 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1079128 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1083. Min Act: -0.0000

Data Index: 958961 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1003. Min Act: -0.0000

Data Index: 414661 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1036. Min Act: 0.0000

Data Index: 412346 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1003. Min Act: -0.0000

Data Index: 1328788 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1136669 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0976. Min Act: -0.0000

Data Index: 631220 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1017987 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0983. Min Act: -0.0000

Data Index: 848950 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1093618 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0936. Min Act: -0.0000

Data Index: 1150374 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0939. Min Act: -0.0000

Data Index: 433357 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0925. Min Act: -0.0000

Data Index: 1068355 (C4 (Web Text))

Max Activating Token Index: 479