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

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

Neuron 4474 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.2713. Min Act: -0.0000

Data Index: 1285892 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.2805. Min Act: -0.0000

Data Index: 315127 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.0827. Min Act: -0.0000

Data Index: 1052472 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.0426. Min Act: -0.0000

Data Index: 755082 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.1100. Min Act: -0.0000

Data Index: 521555 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.1152. Min Act: -0.0000

Data Index: 962806 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.0722. Min Act: -0.0000

Data Index: 1006741 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.0354. Min Act: -0.0000

Data Index: 628456 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.0312. Min Act: -0.0000

Data Index: 241335 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.0912. Min Act: -0.0000

Data Index: 1311594 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.0951. Min Act: -0.0000

Data Index: 1326813 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.9871. Min Act: -0.0000

Data Index: 424731 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.0209. Min Act: -0.0000

Data Index: 581523 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.0135. Min Act: -0.0000

Data Index: 566813 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.0100. Min Act: -0.0000

Data Index: 782988 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.9848. Min Act: -0.0000

Data Index: 385021 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.9583. Min Act: -0.0000

Data Index: 318362 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.9044. Min Act: -0.0000

Data Index: 458599 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.9423. Min Act: -0.0000

Data Index: 1121544 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.0298. Min Act: -0.0000

Data Index: 1026712 (C4 (Web Text))

Max Activating Token Index: 101