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

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

Neuron 4761 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.6944. Min Act: -0.0000

Data Index: 567383 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1316465 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5906. Min Act: -0.0000

Data Index: 831734 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.6220. Min Act: -0.0000

Data Index: 777275 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.6434. Min Act: -0.0000

Data Index: 164956 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.6429. Min Act: -0.0000

Data Index: 709417 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.6158. Min Act: -0.0000

Data Index: 1331614 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1151131 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5538. Min Act: -0.0000

Data Index: 958665 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5335. Min Act: -0.0000

Data Index: 807856 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1310106 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5036. Min Act: -0.0000

Data Index: 847626 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5040. Min Act: -0.0000

Data Index: 719039 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5183. Min Act: -0.0000

Data Index: 872766 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5041. Min Act: -0.0000

Data Index: 392773 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4807. Min Act: -0.0000

Data Index: 858002 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4983. Min Act: -0.0000

Data Index: 878731 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.5170. Min Act: -0.0000

Data Index: 1099925 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4761. Min Act: -0.0000

Data Index: 1317761 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.6960. Min Range: -0.6960

Max Act: 0.4805. Min Act: -0.0000

Data Index: 856280 (C4 (Web Text))

Max Activating Token Index: 1009