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

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

Neuron 4824 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4995. Min Range: -2.4995

Max Act: 2.4995. Min Act: -0.0000

Data Index: 704456 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 2.4995. Min Range: -2.4995

Max Act: 1.8277. Min Act: -0.0000

Data Index: 257236 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 2.4995. Min Range: -2.4995

Max Act: 1.6108. Min Act: -0.0000

Data Index: 375563 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 2.4995. Min Range: -2.4995

Max Act: 1.5996. Min Act: -0.0000

Data Index: 335888 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 2.4995. Min Range: -2.4995

Max Act: 1.6927. Min Act: -0.0000

Data Index: 716845 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 2.4995. Min Range: -2.4995

Max Act: 1.4156. Min Act: -0.0000

Data Index: 367760 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 2.4995. Min Range: -2.4995

Max Act: 1.3036. Min Act: -0.0000

Data Index: 534096 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 2.4995. Min Range: -2.4995

Max Act: 1.2947. Min Act: -0.0000

Data Index: 396842 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 2.4995. Min Range: -2.4995

Max Act: 1.3089. Min Act: -0.0000

Data Index: 401804 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 2.4995. Min Range: -2.4995

Max Act: 1.2354. Min Act: -0.0000

Data Index: 575232 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 2.4995. Min Range: -2.4995

Max Act: 1.3005. Min Act: -0.0000

Data Index: 434030 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 2.4995. Min Range: -2.4995

Max Act: 1.3050. Min Act: -0.0000

Data Index: 1243761 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 2.4995. Min Range: -2.4995

Max Act: 1.2978. Min Act: -0.0000

Data Index: 1324573 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 2.4995. Min Range: -2.4995

Max Act: 1.3725. Min Act: -0.0000

Data Index: 1326452 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 2.4995. Min Range: -2.4995

Max Act: 1.2981. Min Act: -0.0000

Data Index: 1037689 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 2.4995. Min Range: -2.4995

Max Act: 1.2786. Min Act: -0.0000

Data Index: 603091 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 2.4995. Min Range: -2.4995

Max Act: 1.2778. Min Act: -0.0000

Data Index: 260559 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 2.4995. Min Range: -2.4995

Max Act: 1.2731. Min Act: 0.0000

Data Index: 513783 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 2.4995. Min Range: -2.4995

Max Act: 1.2637. Min Act: -0.0000

Data Index: 1235106 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 2.4995. Min Range: -2.4995

Max Act: 1.2470. Min Act: 0.0000

Data Index: 1097509 (C4 (Web Text))

Max Activating Token Index: 182