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

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

Neuron 1550 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.6309. Min Act: -0.0001

Data Index: 598865 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5785. Min Act: -0.0001

Data Index: 223063 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5651. Min Act: -0.0001

Data Index: 685402 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5806. Min Act: -0.0001

Data Index: 1228943 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5682. Min Act: -0.0001

Data Index: 41383 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5890. Min Act: -0.0001

Data Index: 279767 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5262. Min Act: -0.0001

Data Index: 423258 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4787. Min Act: -0.0001

Data Index: 325399 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5109. Min Act: -0.0001

Data Index: 1167059 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4719. Min Act: -0.0001

Data Index: 275575 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4762. Min Act: -0.0001

Data Index: 931345 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4863. Min Act: -0.0001

Data Index: 1154854 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5019. Min Act: -0.0001

Data Index: 549384 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4742. Min Act: -0.0001

Data Index: 564893 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4319. Min Act: -0.0001

Data Index: 1204717 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4576. Min Act: -0.0001

Data Index: 1015598 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4657. Min Act: -0.0001

Data Index: 819000 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4705. Min Act: -0.0001

Data Index: 869153 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4821. Min Act: -0.0001

Data Index: 434477 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4367. Min Act: -0.0001

Data Index: 1174267 (C4 (Web Text))

Max Activating Token Index: 148