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

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

Neuron 5840 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4426. Min Range: -6.4426

Max Act: 6.4426. Min Act: -0.0000

Data Index: 215817 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 6.4426. Min Range: -6.4426

Max Act: 5.9904. Min Act: -0.0000

Data Index: 795594 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 6.4426. Min Range: -6.4426

Max Act: 6.2702. Min Act: -0.0000

Data Index: 523266 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 6.4426. Min Range: -6.4426

Max Act: 5.5333. Min Act: -0.0001

Data Index: 535324 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 6.4426. Min Range: -6.4426

Max Act: 5.3153. Min Act: -0.0000

Data Index: 391198 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 6.4426. Min Range: -6.4426

Max Act: 5.3540. Min Act: -0.0001

Data Index: 978028 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 6.4426. Min Range: -6.4426

Max Act: 5.0764. Min Act: -0.0000

Data Index: 590995 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 6.4426. Min Range: -6.4426

Max Act: 4.6575. Min Act: -0.0000

Data Index: 1261248 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 6.4426. Min Range: -6.4426

Max Act: 4.5783. Min Act: -0.0000

Data Index: 1031901 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 6.4426. Min Range: -6.4426

Max Act: 4.2584. Min Act: -0.0000

Data Index: 1064494 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 6.4426. Min Range: -6.4426

Max Act: 4.2951. Min Act: -0.0000

Data Index: 731652 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 6.4426. Min Range: -6.4426

Max Act: 4.8352. Min Act: -0.0000

Data Index: 424894 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 6.4426. Min Range: -6.4426

Max Act: 4.2594. Min Act: -0.0000

Data Index: 1337634 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 6.4426. Min Range: -6.4426

Max Act: 4.7903. Min Act: -0.0000

Data Index: 1185714 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 6.4426. Min Range: -6.4426

Max Act: 4.6073. Min Act: -0.0000

Data Index: 823486 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 6.4426. Min Range: -6.4426

Max Act: 4.4261. Min Act: -0.0000

Data Index: 1041342 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 6.4426. Min Range: -6.4426

Max Act: 4.7331. Min Act: -0.0000

Data Index: 1327005 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 6.4426. Min Range: -6.4426

Max Act: 4.3918. Min Act: -0.0000

Data Index: 478115 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 6.4426. Min Range: -6.4426

Max Act: 3.8076. Min Act: -0.0000

Data Index: 634390 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 6.4426. Min Range: -6.4426

Max Act: 4.4548. Min Act: -0.0000

Data Index: 353331 (C4 (Web Text))

Max Activating Token Index: 769