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

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

Neuron 3005 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0018. Min Range: -2.0018

Max Act: 2.0018. Min Act: -0.0000

Data Index: 1398499 (Python Code)

Max Activating Token Index: 805

Text #1

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.9352. Min Act: -0.0000

Data Index: 1099819 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.8756. Min Act: -0.0000

Data Index: 446467 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.7439. Min Act: -0.0000

Data Index: 478386 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.8352. Min Act: -0.0000

Data Index: 262672 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.7350. Min Act: -0.0000

Data Index: 568513 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.5782. Min Act: -0.0000

Data Index: 1174404 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.5638. Min Act: -0.0000

Data Index: 525964 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.5336. Min Act: -0.0000

Data Index: 1554010 (Python Code)

Max Activating Token Index: 71

Text #9

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.5089. Min Act: -0.0000

Data Index: 1052495 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.4876. Min Act: -0.0000

Data Index: 481398 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.3828. Min Act: -0.0000

Data Index: 327576 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.4559. Min Act: -0.0000

Data Index: 80670 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.4747. Min Act: -0.0000

Data Index: 328648 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.4619. Min Act: -0.0000

Data Index: 262478 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.3483. Min Act: -0.0000

Data Index: 366270 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.4091. Min Act: -0.0000

Data Index: 220409 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.3164. Min Act: -0.0000

Data Index: 1183003 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.3908. Min Act: -0.0000

Data Index: 42996 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 2.0018. Min Range: -2.0018

Max Act: 1.3774. Min Act: -0.0000

Data Index: 538686 (C4 (Web Text))

Max Activating Token Index: 705