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

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

Neuron 3938 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.8853. Min Act: -0.0000

Data Index: 554926 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.8837. Min Act: -0.0000

Data Index: 498229 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7801. Min Act: -0.0000

Data Index: 53689 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7694. Min Act: -0.0001

Data Index: 801582 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7425. Min Act: -0.0000

Data Index: 573335 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7889. Min Act: -0.0000

Data Index: 1283981 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7540. Min Act: -0.0000

Data Index: 790170 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7340. Min Act: -0.0000

Data Index: 706853 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7696. Min Act: -0.0000

Data Index: 998077 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7471. Min Act: -0.0001

Data Index: 1151078 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7453. Min Act: -0.0001

Data Index: 144204 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7507. Min Act: -0.0001

Data Index: 772652 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7560. Min Act: -0.0001

Data Index: 13694 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7182. Min Act: -0.0000

Data Index: 187138 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7221. Min Act: -0.0001

Data Index: 727354 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7168. Min Act: -0.0000

Data Index: 1096347 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.7082. Min Act: -0.0000

Data Index: 190051 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.6963. Min Act: -0.0001

Data Index: 928559 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.6987. Min Act: -0.0001

Data Index: 881303 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.8853. Min Range: -0.8853

Max Act: 0.6859. Min Act: -0.0001

Data Index: 774486 (C4 (Web Text))

Max Activating Token Index: 809