Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1230 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0758. Min Act: -0.0002

Data Index: 454233 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1294030 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0622. Min Act: -0.0002

Data Index: 580108 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0548. Min Act: -0.0002

Data Index: 309619 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0543. Min Act: -0.0002

Data Index: 889170 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1352510 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0465. Min Act: -0.0002

Data Index: 245608 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1338961 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0524. Min Act: -0.0002

Data Index: 816881 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0470. Min Act: -0.0002

Data Index: 96828 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0489. Min Act: -0.0002

Data Index: 930412 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0450. Min Act: -0.0002

Data Index: 718338 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0426. Min Act: -0.0002

Data Index: 343626 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0431. Min Act: -0.0002

Data Index: 202947 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1108487 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0407. Min Act: -0.0002

Data Index: 619968 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0413. Min Act: -0.0002

Data Index: 806943 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0474. Min Act: -0.0002

Data Index: 278141 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1042965 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0408. Min Act: -0.0002

Data Index: 848400 (C4 (Web Text))

Max Activating Token Index: 182