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

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

Neuron 1199 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.6483. Min Act: -0.0000

Data Index: 640800 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1133819 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.5409. Min Act: -0.0000

Data Index: 910108 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4640. Min Act: -0.0000

Data Index: 499026 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4313. Min Act: -0.0000

Data Index: 155138 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4219. Min Act: -0.0000

Data Index: 920861 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4123. Min Act: -0.0000

Data Index: 417212 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4412. Min Act: -0.0000

Data Index: 878350 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1041237 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4030. Min Act: -0.0000

Data Index: 86707 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3756. Min Act: -0.0000

Data Index: 121741 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3916. Min Act: -0.0000

Data Index: 638564 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3921. Min Act: -0.0000

Data Index: 633008 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3295. Min Act: -0.0000

Data Index: 179782 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1258486 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3518. Min Act: -0.0000

Data Index: 1027584 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3492. Min Act: -0.0000

Data Index: 509941 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3219. Min Act: -0.0000

Data Index: 1325958 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.2974. Min Act: -0.0000

Data Index: 664862 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.2715. Min Act: -0.0000

Data Index: 14795 (C4 (Web Text))

Max Activating Token Index: 269