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

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

Neuron 1020 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5739. Min Act: -0.0001

Data Index: 1068465 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5485. Min Act: -0.0001

Data Index: 503116 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5250. Min Act: -0.0001

Data Index: 99665 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1320274 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5043. Min Act: -0.0000

Data Index: 432995 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4976. Min Act: -0.0000

Data Index: 647157 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4886. Min Act: -0.0001

Data Index: 1049857 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4768. Min Act: -0.0001

Data Index: 258421 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4862. Min Act: -0.0001

Data Index: 511664 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4713. Min Act: -0.0000

Data Index: 980262 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4641. Min Act: -0.0001

Data Index: 338905 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1148044 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4639. Min Act: -0.0000

Data Index: 588358 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1177755 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4574. Min Act: -0.0001

Data Index: 799480 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4284. Min Act: -0.0000

Data Index: 342371 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4510. Min Act: -0.0000

Data Index: 827089 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4718. Min Act: -0.0001

Data Index: 511712 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4667. Min Act: -0.0001

Data Index: 250608 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4622. Min Act: -0.0000

Data Index: 825812 (C4 (Web Text))

Max Activating Token Index: 805