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

Dataset: The Pile

Neuron 732 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3620. Min Act: -0.0000

Data Index: 1107496 (The Pile)

Max Activating Token Index: 763

Text #1

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3409. Min Act: -0.0000

Data Index: 192419 (The Pile)

Max Activating Token Index: 893

Text #2

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2830. Min Act: -0.0000

Data Index: 623220 (The Pile)

Max Activating Token Index: 141

Text #3

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2836. Min Act: -0.0000

Data Index: 408545 (The Pile)

Max Activating Token Index: 562

Text #4

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2482. Min Act: -0.0000

Data Index: 672004 (The Pile)

Max Activating Token Index: 999

Text #5

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2604. Min Act: -0.0000

Data Index: 130136 (The Pile)

Max Activating Token Index: 748

Text #6

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2470. Min Act: -0.0000

Data Index: 550312 (The Pile)

Max Activating Token Index: 167

Text #7

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2382. Min Act: -0.0000

Data Index: 1895753 (The Pile)

Max Activating Token Index: 589

Text #8

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2497. Min Act: -0.0000

Data Index: 1625118 (The Pile)

Max Activating Token Index: 697

Text #9

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2345. Min Act: -0.0000

Data Index: 791108 (The Pile)

Max Activating Token Index: 144

Text #10

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2382. Min Act: -0.0000

Data Index: 1010826 (The Pile)

Max Activating Token Index: 516

Text #11

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2457. Min Act: -0.0000

Data Index: 339124 (The Pile)

Max Activating Token Index: 256

Text #12

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2271. Min Act: -0.0000

Data Index: 730608 (The Pile)

Max Activating Token Index: 301

Text #13

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2379. Min Act: -0.0000

Data Index: 333345 (The Pile)

Max Activating Token Index: 256

Text #14

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2274. Min Act: -0.0000

Data Index: 909628 (The Pile)

Max Activating Token Index: 398

Text #15

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2333. Min Act: -0.0000

Data Index: 691143 (The Pile)

Max Activating Token Index: 464

Text #16

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1888069 (The Pile)

Max Activating Token Index: 318

Text #17

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1880498 (The Pile)

Max Activating Token Index: 496

Text #18

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2121. Min Act: -0.0000

Data Index: 1935455 (The Pile)

Max Activating Token Index: 249

Text #19

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2136. Min Act: -0.0000

Data Index: 515949 (The Pile)

Max Activating Token Index: 750