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

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

Neuron 4144 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.8696. Min Act: -0.0000

Data Index: 267153 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1143824 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.8681. Min Act: -0.0000

Data Index: 1061991 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.7831. Min Act: -0.0000

Data Index: 52060 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.7584. Min Act: -0.0000

Data Index: 356046 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.7461. Min Act: -0.0000

Data Index: 293178 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.7312. Min Act: -0.0000

Data Index: 936067 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.7379. Min Act: -0.0000

Data Index: 1239939 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.7261. Min Act: -0.0000

Data Index: 412933 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.7934. Min Act: -0.0000

Data Index: 1301253 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.7579. Min Act: -0.0000

Data Index: 605652 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.6849. Min Act: -0.0000

Data Index: 920353 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.6453. Min Act: -0.0000

Data Index: 514191 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1075260 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.6495. Min Act: -0.0000

Data Index: 1257916 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.7143. Min Act: -0.0000

Data Index: 78887 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.6903. Min Act: -0.0000

Data Index: 1141374 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.6803. Min Act: -0.0000

Data Index: 946141 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.6812. Min Act: -0.0000

Data Index: 477857 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.7095. Min Act: -0.0000

Data Index: 251395 (C4 (Web Text))

Max Activating Token Index: 1009