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

Dataset: The Pile

Neuron 1593 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.3268. Min Act: -0.0000

Data Index: 1545017 (The Pile)

Max Activating Token Index: 641

Text #1

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.2714. Min Act: -0.0001

Data Index: 1334172 (The Pile)

Max Activating Token Index: 714

Text #2

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.2005. Min Act: -0.0000

Data Index: 712499 (The Pile)

Max Activating Token Index: 880

Text #3

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.1969. Min Act: -0.0000

Data Index: 519227 (The Pile)

Max Activating Token Index: 883

Text #4

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.1040. Min Act: -0.0000

Data Index: 445724 (The Pile)

Max Activating Token Index: 488

Text #5

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.1095. Min Act: -0.0000

Data Index: 1550517 (The Pile)

Max Activating Token Index: 889

Text #6

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.0596. Min Act: -0.0000

Data Index: 899852 (The Pile)

Max Activating Token Index: 934

Text #7

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.0541. Min Act: -0.0000

Data Index: 398404 (The Pile)

Max Activating Token Index: 1017

Text #8

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.9979. Min Act: -0.0000

Data Index: 1372245 (The Pile)

Max Activating Token Index: 550

Text #9

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.0382. Min Act: -0.0000

Data Index: 455381 (The Pile)

Max Activating Token Index: 318

Text #10

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.0982. Min Act: -0.0000

Data Index: 908784 (The Pile)

Max Activating Token Index: 685

Text #11

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.9755. Min Act: -0.0000

Data Index: 1685840 (The Pile)

Max Activating Token Index: 717

Text #12

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.9714. Min Act: -0.0000

Data Index: 1743943 (The Pile)

Max Activating Token Index: 226

Text #13

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.9459. Min Act: -0.0000

Data Index: 1711780 (The Pile)

Max Activating Token Index: 624

Text #14

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.8944. Min Act: -0.0000

Data Index: 1477879 (The Pile)

Max Activating Token Index: 627

Text #15

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.9331. Min Act: -0.0000

Data Index: 1290982 (The Pile)

Max Activating Token Index: 726

Text #16

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.9569. Min Act: -0.0000

Data Index: 1823908 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.8588. Min Act: -0.0000

Data Index: 826819 (The Pile)

Max Activating Token Index: 993

Text #18

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.9278. Min Act: -0.0000

Data Index: 21679 (The Pile)

Max Activating Token Index: 220

Text #19

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.8718. Min Act: -0.0000

Data Index: 1405211 (The Pile)

Max Activating Token Index: 605