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

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

Neuron 2246 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.8911. Min Act: -0.0001

Data Index: 1282861 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.7646. Min Act: -0.0001

Data Index: 898761 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.7542. Min Act: -0.0001

Data Index: 517525 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.7099. Min Act: -0.0001

Data Index: 1420019 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6767. Min Act: -0.0001

Data Index: 533562 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1025032 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6412. Min Act: -0.0000

Data Index: 573588 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6422. Min Act: -0.0001

Data Index: 1200019 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.5881. Min Act: -0.0001

Data Index: 1019404 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.5927. Min Act: -0.0001

Data Index: 316656 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6037. Min Act: -0.0001

Data Index: 985659 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.5421. Min Act: -0.0001

Data Index: 1546965 (Python Code)

Max Activating Token Index: 99

Text #12

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.5035. Min Act: -0.0000

Data Index: 958970 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.5150. Min Act: -0.0001

Data Index: 172174 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.5405. Min Act: -0.0001

Data Index: 182268 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.5004. Min Act: -0.0001

Data Index: 981603 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.5139. Min Act: -0.0001

Data Index: 1423567 (Python Code)

Max Activating Token Index: 192

Text #17

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.4678. Min Act: -0.0001

Data Index: 1077713 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.5080. Min Act: -0.0001

Data Index: 1341373 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.4577. Min Act: -0.0001

Data Index: 1455945 (Python Code)

Max Activating Token Index: 176