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

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

Neuron 4304 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4180. Min Range: -0.4180

Max Act: 0.4180. Min Act: -0.0001

Data Index: 925791 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.4180. Min Range: -0.4180

Max Act: 0.4143. Min Act: -0.0001

Data Index: 316227 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.4180. Min Range: -0.4180

Max Act: 0.3843. Min Act: -0.0001

Data Index: 1191463 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.4180. Min Range: -0.4180

Max Act: 0.3818. Min Act: -0.0001

Data Index: 747453 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.4180. Min Range: -0.4180

Max Act: 0.3935. Min Act: -0.0001

Data Index: 307189 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.4180. Min Range: -0.4180

Max Act: 0.3848. Min Act: -0.0001

Data Index: 1088606 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.4180. Min Range: -0.4180

Max Act: 0.3762. Min Act: -0.0001

Data Index: 211579 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 0.4180. Min Range: -0.4180

Max Act: 0.3750. Min Act: -0.0001

Data Index: 671370 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.4180. Min Range: -0.4180

Max Act: 0.3622. Min Act: -0.0001

Data Index: 821927 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.4180. Min Range: -0.4180

Max Act: 0.3710. Min Act: -0.0001

Data Index: 229648 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.4180. Min Range: -0.4180

Max Act: 0.3819. Min Act: -0.0001

Data Index: 1121470 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.4180. Min Range: -0.4180

Max Act: 0.3737. Min Act: -0.0001

Data Index: 662930 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 0.4180. Min Range: -0.4180

Max Act: 0.3659. Min Act: -0.0001

Data Index: 872847 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.4180. Min Range: -0.4180

Max Act: 0.3620. Min Act: -0.0001

Data Index: 469422 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.4180. Min Range: -0.4180

Max Act: 0.3446. Min Act: -0.0001

Data Index: 178888 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.4180. Min Range: -0.4180

Max Act: 0.3432. Min Act: -0.0001

Data Index: 660109 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 0.4180. Min Range: -0.4180

Max Act: 0.3450. Min Act: -0.0001

Data Index: 1182865 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.4180. Min Range: -0.4180

Max Act: 0.3429. Min Act: -0.0001

Data Index: 456317 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.4180. Min Range: -0.4180

Max Act: 0.3398. Min Act: -0.0001

Data Index: 501729 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 0.4180. Min Range: -0.4180

Max Act: 0.3400. Min Act: -0.0001

Data Index: 1345814 (C4 (Web Text))

Max Activating Token Index: 246