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

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

Neuron 2232 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.7003. Min Act: -0.0000

Data Index: 79499 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6154. Min Act: -0.0000

Data Index: 950060 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5717. Min Act: -0.0000

Data Index: 326469 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1092232 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5535. Min Act: -0.0000

Data Index: 838075 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1185381 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5367. Min Act: -0.0000

Data Index: 592761 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5337. Min Act: -0.0000

Data Index: 246481 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5372. Min Act: -0.0000

Data Index: 82013 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1321657 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1070681 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5091. Min Act: -0.0000

Data Index: 926766 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4935. Min Act: -0.0000

Data Index: 596847 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4931. Min Act: -0.0000

Data Index: 1050879 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5123. Min Act: 0.0000

Data Index: 857536 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1646462 (Python Code)

Max Activating Token Index: 614

Text #16

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4775. Min Act: -0.0000

Data Index: 243902 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4970. Min Act: -0.0001

Data Index: 70913 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4916. Min Act: -0.0000

Data Index: 155296 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.4895. Min Act: -0.0000

Data Index: 780391 (C4 (Web Text))

Max Activating Token Index: 476