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

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

Neuron 836 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5900. Min Act: -0.0001

Data Index: 341101 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.6053. Min Act: -0.0001

Data Index: 855993 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5477. Min Act: -0.0001

Data Index: 901002 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5669. Min Act: -0.0001

Data Index: 461035 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5538. Min Act: -0.0001

Data Index: 511246 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5521. Min Act: -0.0001

Data Index: 575743 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5515. Min Act: -0.0001

Data Index: 236521 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5040. Min Act: -0.0001

Data Index: 872355 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5376. Min Act: -0.0001

Data Index: 1171255 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5357. Min Act: -0.0001

Data Index: 1029825 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4984. Min Act: -0.0001

Data Index: 1649610 (Python Code)

Max Activating Token Index: 21

Text #11

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5118. Min Act: -0.0001

Data Index: 260658 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4592. Min Act: -0.0001

Data Index: 1204110 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5103. Min Act: -0.0001

Data Index: 301897 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5004. Min Act: -0.0001

Data Index: 908465 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4966. Min Act: -0.0001

Data Index: 624128 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5008. Min Act: -0.0001

Data Index: 587129 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4674. Min Act: -0.0001

Data Index: 356376 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5146. Min Act: -0.0001

Data Index: 1342816 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4989. Min Act: -0.0001

Data Index: 123357 (C4 (Web Text))

Max Activating Token Index: 156