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

Dataset: The Pile

Neuron 1386 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.7568. Min Act: -0.0000

Data Index: 1768957 (The Pile)

Max Activating Token Index: 180

Text #1

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.8268. Min Act: -0.0000

Data Index: 1170504 (The Pile)

Max Activating Token Index: 981

Text #2

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6381. Min Act: -0.0000

Data Index: 1328036 (The Pile)

Max Activating Token Index: 476

Text #3

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.0398. Min Act: -0.0000

Data Index: 1554393 (The Pile)

Max Activating Token Index: 613

Text #4

Max Range: 3.8268. Min Range: -3.8268

Max Act: 2.6976. Min Act: -0.0000

Data Index: 114646 (The Pile)

Max Activating Token Index: 769

Text #5

Max Range: 3.8268. Min Range: -3.8268

Max Act: 2.6894. Min Act: -0.0000

Data Index: 1311924 (The Pile)

Max Activating Token Index: 267

Text #6

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.1082. Min Act: -0.0000

Data Index: 163444 (The Pile)

Max Activating Token Index: 443

Text #7

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.2237. Min Act: -0.0000

Data Index: 1001118 (The Pile)

Max Activating Token Index: 802

Text #8

Max Range: 3.8268. Min Range: -3.8268

Max Act: 2.9378. Min Act: -0.0000

Data Index: 1535933 (The Pile)

Max Activating Token Index: 707

Text #9

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.0445. Min Act: -0.0000

Data Index: 1726394 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 3.8268. Min Range: -3.8268

Max Act: 2.9943. Min Act: -0.0000

Data Index: 655182 (The Pile)

Max Activating Token Index: 395

Text #11

Max Range: 3.8268. Min Range: -3.8268

Max Act: 2.9723. Min Act: -0.0000

Data Index: 1985144 (The Pile)

Max Activating Token Index: 534

Text #12

Max Range: 3.8268. Min Range: -3.8268

Max Act: 2.9598. Min Act: -0.0000

Data Index: 1962964 (The Pile)

Max Activating Token Index: 220

Text #13

Max Range: 3.8268. Min Range: -3.8268

Max Act: 2.6578. Min Act: -0.0000

Data Index: 1180017 (The Pile)

Max Activating Token Index: 496

Text #14

Max Range: 3.8268. Min Range: -3.8268

Max Act: 2.6673. Min Act: -0.0000

Data Index: 672116 (The Pile)

Max Activating Token Index: 588

Text #15

Max Range: 3.8268. Min Range: -3.8268

Max Act: 2.8128. Min Act: -0.0000

Data Index: 860517 (The Pile)

Max Activating Token Index: 660

Text #16

Max Range: 3.8268. Min Range: -3.8268

Max Act: 2.7717. Min Act: -0.0000

Data Index: 1561969 (The Pile)

Max Activating Token Index: 99

Text #17

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.0411. Min Act: -0.0000

Data Index: 1511734 (The Pile)

Max Activating Token Index: 550

Text #18

Max Range: 3.8268. Min Range: -3.8268

Max Act: 2.9837. Min Act: -0.0000

Data Index: 1053736 (The Pile)

Max Activating Token Index: 546

Text #19

Max Range: 3.8268. Min Range: -3.8268

Max Act: 2.8669. Min Act: -0.0000

Data Index: 32559 (The Pile)

Max Activating Token Index: 410