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

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

Neuron 4057 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1529020 (Python Code)

Max Activating Token Index: 521

Text #1

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1504486 (Python Code)

Max Activating Token Index: 464

Text #2

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.5063. Min Act: -0.0000

Data Index: 1550617 (Python Code)

Max Activating Token Index: 565

Text #3

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1473334 (Python Code)

Max Activating Token Index: 93

Text #4

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.5053. Min Act: -0.0000

Data Index: 304918 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4756. Min Act: -0.0000

Data Index: 1585357 (Python Code)

Max Activating Token Index: 464

Text #6

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4824. Min Act: -0.0000

Data Index: 1416174 (Python Code)

Max Activating Token Index: 382

Text #7

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.5042. Min Act: -0.0000

Data Index: 646593 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4887. Min Act: -0.0000

Data Index: 1609970 (Python Code)

Max Activating Token Index: 727

Text #9

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4671. Min Act: -0.0000

Data Index: 1085765 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1646314 (Python Code)

Max Activating Token Index: 153

Text #11

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1435398 (Python Code)

Max Activating Token Index: 200

Text #12

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4362. Min Act: -0.0000

Data Index: 1531946 (Python Code)

Max Activating Token Index: 141

Text #13

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.5221. Min Act: -0.0000

Data Index: 1477917 (Python Code)

Max Activating Token Index: 122

Text #14

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4815. Min Act: -0.0000

Data Index: 1630222 (Python Code)

Max Activating Token Index: 544

Text #15

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1602063 (Python Code)

Max Activating Token Index: 151

Text #16

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.5204. Min Act: -0.0000

Data Index: 473668 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4685. Min Act: -0.0000

Data Index: 615844 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4253. Min Act: -0.0000

Data Index: 97828 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.3985. Min Act: -0.0000

Data Index: 788559 (C4 (Web Text))

Max Activating Token Index: 1003