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

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

Neuron 958 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: 0.3106. Min Range: -0.3106

Max Act: 0.3106. Min Act: -0.0001

Data Index: 1037798 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.3106. Min Range: -0.3106

Max Act: 0.2884. Min Act: -0.0001

Data Index: 314612 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 0.3106. Min Range: -0.3106

Max Act: 0.2681. Min Act: -0.0000

Data Index: 418949 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 0.3106. Min Range: -0.3106

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1008146 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.3106. Min Range: -0.3106

Max Act: 0.2332. Min Act: -0.0000

Data Index: 580236 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.3106. Min Range: -0.3106

Max Act: 0.2277. Min Act: -0.0000

Data Index: 14479 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.3106. Min Range: -0.3106

Max Act: 0.2262. Min Act: -0.0001

Data Index: 353493 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.3106. Min Range: -0.3106

Max Act: 0.2196. Min Act: -0.0001

Data Index: 967706 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.3106. Min Range: -0.3106

Max Act: 0.2057. Min Act: -0.0000

Data Index: 227324 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.3106. Min Range: -0.3106

Max Act: 0.2086. Min Act: -0.0000

Data Index: 1102968 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 0.3106. Min Range: -0.3106

Max Act: 0.2020. Min Act: -0.0001

Data Index: 1464389 (Python Code)

Max Activating Token Index: 404

Text #11

Max Range: 0.3106. Min Range: -0.3106

Max Act: 0.1809. Min Act: -0.0001

Data Index: 56233 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.3106. Min Range: -0.3106

Max Act: 0.1935. Min Act: -0.0001

Data Index: 1608920 (Python Code)

Max Activating Token Index: 34

Text #13

Max Range: 0.3106. Min Range: -0.3106

Max Act: 0.1997. Min Act: -0.0001

Data Index: 1366883 (Python Code)

Max Activating Token Index: 625

Text #14

Max Range: 0.3106. Min Range: -0.3106

Max Act: 0.1827. Min Act: -0.0000

Data Index: 1094603 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.3106. Min Range: -0.3106

Max Act: 0.1787. Min Act: -0.0000

Data Index: 212718 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.3106. Min Range: -0.3106

Max Act: 0.1726. Min Act: -0.0000

Data Index: 163066 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.3106. Min Range: -0.3106

Max Act: 0.1771. Min Act: -0.0000

Data Index: 158750 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.3106. Min Range: -0.3106

Max Act: 0.1774. Min Act: -0.0001

Data Index: 337986 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.3106. Min Range: -0.3106

Max Act: 0.1869. Min Act: -0.0000

Data Index: 568368 (C4 (Web Text))

Max Activating Token Index: 920