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

Dataset: The Pile

Neuron 1520 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: 0.7342. Min Range: -0.7342

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1849147 (The Pile)

Max Activating Token Index: 491

Text #1

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.7342. Min Act: -0.0000

Data Index: 709107 (The Pile)

Max Activating Token Index: 444

Text #2

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1947330 (The Pile)

Max Activating Token Index: 212

Text #3

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.6318. Min Act: -0.0000

Data Index: 1077253 (The Pile)

Max Activating Token Index: 730

Text #4

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.6665. Min Act: -0.0000

Data Index: 472905 (The Pile)

Max Activating Token Index: 268

Text #5

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.6426. Min Act: -0.0000

Data Index: 1264648 (The Pile)

Max Activating Token Index: 375

Text #6

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5946. Min Act: -0.0000

Data Index: 301191 (The Pile)

Max Activating Token Index: 420

Text #7

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.6052. Min Act: -0.0000

Data Index: 918689 (The Pile)

Max Activating Token Index: 236

Text #8

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.6221. Min Act: -0.0000

Data Index: 1008233 (The Pile)

Max Activating Token Index: 300

Text #9

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5806. Min Act: -0.0000

Data Index: 499709 (The Pile)

Max Activating Token Index: 292

Text #10

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5948. Min Act: -0.0000

Data Index: 1073460 (The Pile)

Max Activating Token Index: 586

Text #11

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1370378 (The Pile)

Max Activating Token Index: 505

Text #12

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.6078. Min Act: -0.0000

Data Index: 208075 (The Pile)

Max Activating Token Index: 93

Text #13

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1310756 (The Pile)

Max Activating Token Index: 319

Text #14

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5995. Min Act: -0.0000

Data Index: 205667 (The Pile)

Max Activating Token Index: 747

Text #15

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5734. Min Act: -0.0000

Data Index: 1177872 (The Pile)

Max Activating Token Index: 194

Text #16

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1006432 (The Pile)

Max Activating Token Index: 794

Text #17

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1954384 (The Pile)

Max Activating Token Index: 635

Text #18

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1068685 (The Pile)

Max Activating Token Index: 341

Text #19

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1138953 (The Pile)

Max Activating Token Index: 440