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

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

Neuron 1666 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3488. Min Act: -0.0000

Data Index: 1208357 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1397969 (Python Code)

Max Activating Token Index: 860

Text #2

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3281. Min Act: -0.0000

Data Index: 1605596 (Python Code)

Max Activating Token Index: 979

Text #3

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3054. Min Act: -0.0000

Data Index: 81201 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3203. Min Act: -0.0000

Data Index: 1577066 (Python Code)

Max Activating Token Index: 854

Text #5

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2968. Min Act: -0.0000

Data Index: 1467769 (Python Code)

Max Activating Token Index: 888

Text #6

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1381428 (Python Code)

Max Activating Token Index: 590

Text #7

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3140. Min Act: -0.0000

Data Index: 1071099 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2942. Min Act: -0.0000

Data Index: 186838 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2915. Min Act: -0.0000

Data Index: 946508 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2792. Min Act: -0.0000

Data Index: 909690 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1367777 (Python Code)

Max Activating Token Index: 427

Text #12

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2706. Min Act: -0.0000

Data Index: 43127 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2836. Min Act: -0.0000

Data Index: 606470 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2919. Min Act: -0.0000

Data Index: 912001 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1377712 (Python Code)

Max Activating Token Index: 410

Text #16

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2742. Min Act: -0.0000

Data Index: 668757 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2638. Min Act: -0.0000

Data Index: 1032118 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2829. Min Act: -0.0000

Data Index: 1064095 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2662. Min Act: -0.0000

Data Index: 989826 (C4 (Web Text))

Max Activating Token Index: 517