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

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

Neuron 526 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1571777 (Python Code)

Max Activating Token Index: 632

Text #1

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0934. Min Act: -0.0002

Data Index: 1110505 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0931. Min Act: -0.0002

Data Index: 80941 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0915. Min Act: -0.0002

Data Index: 973023 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0938. Min Act: -0.0002

Data Index: 788227 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0909. Min Act: -0.0002

Data Index: 186902 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0876. Min Act: -0.0002

Data Index: 495630 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1338555 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0884. Min Act: -0.0002

Data Index: 44393 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0877. Min Act: -0.0002

Data Index: 366618 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1600083 (Python Code)

Max Activating Token Index: 156

Text #11

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0869. Min Act: -0.0002

Data Index: 568880 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1430059 (Python Code)

Max Activating Token Index: 345

Text #13

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0843. Min Act: -0.0002

Data Index: 366213 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0854. Min Act: -0.0002

Data Index: 332451 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0835. Min Act: -0.0002

Data Index: 445985 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0842. Min Act: -0.0002

Data Index: 788525 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0847. Min Act: -0.0002

Data Index: 583134 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0828. Min Act: -0.0002

Data Index: 1431036 (Python Code)

Max Activating Token Index: 415

Text #19

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0813. Min Act: -0.0002

Data Index: 631655 (C4 (Web Text))

Max Activating Token Index: 94