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

Dataset: The Pile

Neuron 4690 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: 0.7353. Min Range: -0.7353

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1788519 (The Pile)

Max Activating Token Index: 273

Text #1

Max Range: 0.7353. Min Range: -0.7353

Max Act: 0.5831. Min Act: -0.0000

Data Index: 122407 (The Pile)

Max Activating Token Index: 692

Text #2

Max Range: 0.7353. Min Range: -0.7353

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1410349 (The Pile)

Max Activating Token Index: 132

Text #3

Max Range: 0.7353. Min Range: -0.7353

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1249199 (The Pile)

Max Activating Token Index: 680

Text #4

Max Range: 0.7353. Min Range: -0.7353

Max Act: 0.5600. Min Act: -0.0000

Data Index: 183052 (The Pile)

Max Activating Token Index: 801

Text #5

Max Range: 0.7353. Min Range: -0.7353

Max Act: 0.5727. Min Act: -0.0000

Data Index: 132550 (The Pile)

Max Activating Token Index: 720

Text #6

Max Range: 0.7353. Min Range: -0.7353

Max Act: 0.5595. Min Act: -0.0000

Data Index: 369085 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 0.7353. Min Range: -0.7353

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1798343 (The Pile)

Max Activating Token Index: 337

Text #8

Max Range: 0.7353. Min Range: -0.7353

Max Act: 0.4994. Min Act: -0.0000

Data Index: 365682 (The Pile)

Max Activating Token Index: 419

Text #9

Max Range: 0.7353. Min Range: -0.7353

Max Act: 0.5402. Min Act: -0.0000

Data Index: 771409 (The Pile)

Max Activating Token Index: 182

Text #10

Max Range: 0.7353. Min Range: -0.7353

Max Act: 0.4883. Min Act: -0.0000

Data Index: 1289221 (The Pile)

Max Activating Token Index: 377

Text #11

Max Range: 0.7353. Min Range: -0.7353

Max Act: 0.4923. Min Act: -0.0000

Data Index: 55774 (The Pile)

Max Activating Token Index: 469

Text #12

Max Range: 0.7353. Min Range: -0.7353

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1690769 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 0.7353. Min Range: -0.7353

Max Act: 0.4689. Min Act: -0.0000

Data Index: 305361 (The Pile)

Max Activating Token Index: 252

Text #14

Max Range: 0.7353. Min Range: -0.7353

Max Act: 0.4454. Min Act: -0.0000

Data Index: 339064 (The Pile)

Max Activating Token Index: 924

Text #15

Max Range: 0.7353. Min Range: -0.7353

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1971762 (The Pile)

Max Activating Token Index: 587

Text #16

Max Range: 0.7353. Min Range: -0.7353

Max Act: 0.4390. Min Act: -0.0000

Data Index: 526187 (The Pile)

Max Activating Token Index: 220

Text #17

Max Range: 0.7353. Min Range: -0.7353

Max Act: 0.4391. Min Act: -0.0000

Data Index: 238987 (The Pile)

Max Activating Token Index: 384

Text #18

Max Range: 0.7353. Min Range: -0.7353

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1614297 (The Pile)

Max Activating Token Index: 595

Text #19

Max Range: 0.7353. Min Range: -0.7353

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1020516 (The Pile)

Max Activating Token Index: 351