Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 572 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3693. Min Act: -0.0000

Data Index: 197636 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3641. Min Act: -0.0000

Data Index: 668113 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3466. Min Act: -0.0000

Data Index: 1352530 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3268. Min Act: -0.0000

Data Index: 778707 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3194. Min Act: -0.0001

Data Index: 336371 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3282. Min Act: -0.0000

Data Index: 495414 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3120. Min Act: -0.0001

Data Index: 549166 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1159256 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2988. Min Act: -0.0000

Data Index: 900268 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1179137 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3194. Min Act: -0.0001

Data Index: 609618 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3276. Min Act: -0.0000

Data Index: 543691 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1031781 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3071. Min Act: -0.0001

Data Index: 189415 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3024. Min Act: -0.0001

Data Index: 1046803 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3070. Min Act: -0.0001

Data Index: 1232779 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3125. Min Act: -0.0001

Data Index: 972773 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2913. Min Act: -0.0000

Data Index: 61799 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.3021. Min Act: -0.0000

Data Index: 1267456 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.3693. Min Range: -0.3693

Max Act: 0.2912. Min Act: -0.0000

Data Index: 574469 (C4 (Web Text))

Max Activating Token Index: 243