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

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

Neuron 1652 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: 1.2055. Min Range: -1.2055

Max Act: 1.2055. Min Act: -0.0000

Data Index: 652150 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.0703. Min Act: -0.0000

Data Index: 507700 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.0327. Min Act: -0.0000

Data Index: 1326350 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.1125. Min Act: -0.0001

Data Index: 3552 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.9504. Min Act: -0.0000

Data Index: 1044135 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 1.2055. Min Range: -1.2055

Max Act: 1.0042. Min Act: -0.0001

Data Index: 823913 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.9686. Min Act: -0.0000

Data Index: 992335 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.8786. Min Act: -0.0000

Data Index: 1149944 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.8972. Min Act: -0.0000

Data Index: 613650 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.9544. Min Act: -0.0000

Data Index: 846851 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.9070. Min Act: -0.0001

Data Index: 687177 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.9374. Min Act: -0.0000

Data Index: 749662 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.8384. Min Act: -0.0000

Data Index: 367541 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.8647. Min Act: -0.0000

Data Index: 13362 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.9106. Min Act: -0.0000

Data Index: 442002 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.8774. Min Act: -0.0000

Data Index: 395745 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.8736. Min Act: -0.0000

Data Index: 245567 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.8721. Min Act: -0.0000

Data Index: 741263 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.8578. Min Act: -0.0000

Data Index: 1048080 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 1.2055. Min Range: -1.2055

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1300459 (C4 (Web Text))

Max Activating Token Index: 552