Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3162 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.6490. Min Act: -0.0000

Data Index: 917156 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4897. Min Act: -0.0000

Data Index: 707318 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.5285. Min Act: -0.0000

Data Index: 1215880 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.5900. Min Act: -0.0000

Data Index: 173010 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.5879. Min Act: -0.0000

Data Index: 559025 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.5620. Min Act: -0.0000

Data Index: 1028925 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.5730. Min Act: -0.0000

Data Index: 862531 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4828. Min Act: -0.0000

Data Index: 882890 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4479. Min Act: -0.0000

Data Index: 527314 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.5511. Min Act: -0.0000

Data Index: 721889 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4469. Min Act: -0.0000

Data Index: 381949 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4300. Min Act: -0.0000

Data Index: 366207 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.5135. Min Act: -0.0000

Data Index: 499729 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.5842. Min Act: -0.0000

Data Index: 187340 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.5649. Min Act: -0.0000

Data Index: 1203917 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.5537. Min Act: -0.0000

Data Index: 91873 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.3837. Min Act: -0.0000

Data Index: 1201193 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.3053. Min Act: -0.0000

Data Index: 790988 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.5242. Min Act: -0.0000

Data Index: 1216761 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4524. Min Act: -0.0000

Data Index: 883418 (C4 (Web Text))

Max Activating Token Index: 1007