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

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

Neuron 5051 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1051. Min Range: -1.1051

Max Act: 1.1051. Min Act: -0.0000

Data Index: 622072 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 1.1051. Min Range: -1.1051

Max Act: 1.1046. Min Act: -0.0000

Data Index: 1150226 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 1.1051. Min Range: -1.1051

Max Act: 1.0239. Min Act: -0.0000

Data Index: 514023 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 1.1051. Min Range: -1.1051

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1163238 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 1.1051. Min Range: -1.1051

Max Act: 0.8924. Min Act: 0.0001

Data Index: 304893 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 1.1051. Min Range: -1.1051

Max Act: 0.8661. Min Act: 0.0000

Data Index: 219385 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 1.1051. Min Range: -1.1051

Max Act: 0.8701. Min Act: -0.0000

Data Index: 1575514 (Python Code)

Max Activating Token Index: 745

Text #7

Max Range: 1.1051. Min Range: -1.1051

Max Act: 0.8686. Min Act: -0.0000

Data Index: 149315 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 1.1051. Min Range: -1.1051

Max Act: 0.8431. Min Act: -0.0000

Data Index: 310831 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 1.1051. Min Range: -1.1051

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1286271 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 1.1051. Min Range: -1.1051

Max Act: 0.8466. Min Act: -0.0000

Data Index: 427305 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 1.1051. Min Range: -1.1051

Max Act: 0.8564. Min Act: -0.0000

Data Index: 725666 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 1.1051. Min Range: -1.1051

Max Act: 0.8464. Min Act: 0.0000

Data Index: 1032769 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 1.1051. Min Range: -1.1051

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1539857 (Python Code)

Max Activating Token Index: 694

Text #14

Max Range: 1.1051. Min Range: -1.1051

Max Act: 0.7958. Min Act: -0.0000

Data Index: 792576 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 1.1051. Min Range: -1.1051

Max Act: 0.8036. Min Act: -0.0000

Data Index: 621457 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 1.1051. Min Range: -1.1051

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1186460 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 1.1051. Min Range: -1.1051

Max Act: 0.8203. Min Act: -0.0000

Data Index: 346601 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 1.1051. Min Range: -1.1051

Max Act: 0.7900. Min Act: -0.0000

Data Index: 1074102 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 1.1051. Min Range: -1.1051

Max Act: 0.7853. Min Act: -0.0000

Data Index: 682027 (C4 (Web Text))

Max Activating Token Index: 46