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

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

Neuron 2969 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: 1.0365. Min Range: -1.0365

Max Act: 1.0365. Min Act: -0.0001

Data Index: 953183 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.7301. Min Act: -0.0001

Data Index: 592665 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6581. Min Act: -0.0000

Data Index: 585765 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6910. Min Act: -0.0001

Data Index: 631832 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.6725. Min Act: -0.0000

Data Index: 130398 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1196810 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5880. Min Act: -0.0000

Data Index: 1255775 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5979. Min Act: -0.0001

Data Index: 1211779 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5740. Min Act: -0.0000

Data Index: 1302838 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5519. Min Act: -0.0000

Data Index: 279739 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5527. Min Act: -0.0000

Data Index: 40008 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5615. Min Act: 0.0001

Data Index: 786125 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5375. Min Act: -0.0000

Data Index: 506513 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5529. Min Act: -0.0000

Data Index: 284769 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5655. Min Act: -0.0000

Data Index: 108935 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5281. Min Act: 0.0001

Data Index: 107702 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5302. Min Act: -0.0000

Data Index: 643697 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1044592 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5087. Min Act: -0.0001

Data Index: 548073 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 1.0365. Min Range: -1.0365

Max Act: 0.5233. Min Act: 0.0001

Data Index: 370618 (C4 (Web Text))

Max Activating Token Index: 83