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

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

Neuron 3364 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.7806. Min Act: -0.0000

Data Index: 310298 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.7181. Min Act: -0.0000

Data Index: 597145 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6421. Min Act: -0.0000

Data Index: 566296 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6324. Min Act: -0.0000

Data Index: 339253 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5685. Min Act: -0.0000

Data Index: 13437 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5755. Min Act: -0.0000

Data Index: 189977 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5901. Min Act: -0.0000

Data Index: 799419 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6078. Min Act: -0.0000

Data Index: 251693 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1030429 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1170315 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1117137 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5907. Min Act: -0.0000

Data Index: 606996 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5546. Min Act: -0.0000

Data Index: 30593 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5403. Min Act: -0.0000

Data Index: 405360 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5523. Min Act: 0.0000

Data Index: 664094 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5554. Min Act: -0.0000

Data Index: 194598 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1140643 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5252. Min Act: -0.0000

Data Index: 763399 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5192. Min Act: -0.0000

Data Index: 599008 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1345785 (C4 (Web Text))

Max Activating Token Index: 782