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

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

Neuron 1834 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: 1.1503. Min Range: -1.1503

Max Act: 1.1503. Min Act: -0.0001

Data Index: 1297143 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9929. Min Act: -0.0001

Data Index: 743312 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 1.1503. Min Range: -1.1503

Max Act: 1.0102. Min Act: -0.0000

Data Index: 1024720 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9522. Min Act: -0.0000

Data Index: 649299 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9493. Min Act: -0.0000

Data Index: 404254 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.8347. Min Act: -0.0001

Data Index: 734002 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.7961. Min Act: -0.0000

Data Index: 844635 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.8063. Min Act: -0.0000

Data Index: 1124766 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.7247. Min Act: -0.0001

Data Index: 1201709 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.7402. Min Act: -0.0001

Data Index: 198719 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.7394. Min Act: -0.0001

Data Index: 937899 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.7457. Min Act: -0.0001

Data Index: 462458 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.7314. Min Act: -0.0001

Data Index: 507164 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.6736. Min Act: -0.0001

Data Index: 1347446 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.6612. Min Act: -0.0001

Data Index: 1144087 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.5951. Min Act: -0.0001

Data Index: 783503 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.6328. Min Act: -0.0000

Data Index: 920511 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.6433. Min Act: -0.0001

Data Index: 800873 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.5858. Min Act: -0.0001

Data Index: 1251002 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.6353. Min Act: -0.0001

Data Index: 309543 (C4 (Web Text))

Max Activating Token Index: 33