Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2021 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2624. Min Act: -0.0001

Data Index: 954118 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2560. Min Act: -0.0001

Data Index: 1062841 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2486. Min Act: -0.0001

Data Index: 1014860 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2612. Min Act: -0.0001

Data Index: 1256656 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2047. Min Act: -0.0001

Data Index: 571335 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.2128. Min Act: -0.0001

Data Index: 342035 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.1948. Min Act: -0.0001

Data Index: 1193361 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.1701. Min Act: -0.0001

Data Index: 988852 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.1967. Min Act: -0.0001

Data Index: 274736 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.1806. Min Act: -0.0001

Data Index: 488005 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.1731. Min Act: -0.0001

Data Index: 72152 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.1660. Min Act: -0.0001

Data Index: 661283 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.1729. Min Act: -0.0001

Data Index: 16334 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.1659. Min Act: -0.0001

Data Index: 598982 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.1662. Min Act: -0.0001

Data Index: 1020943 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.1452. Min Act: -0.0001

Data Index: 338836 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.1675. Min Act: -0.0001

Data Index: 182869 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.1587. Min Act: -0.0001

Data Index: 451224 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.1609. Min Act: -0.0001

Data Index: 1118601 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.2624. Min Range: -0.2624

Max Act: 0.1467. Min Act: -0.0001

Data Index: 440274 (C4 (Web Text))

Max Activating Token Index: 218