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

Dataset: The Pile

Neuron 3189 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0322. Min Range: -1.0322

Max Act: 1.0322. Min Act: -0.0000

Data Index: 1769487 (The Pile)

Max Activating Token Index: 194

Text #1

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.7651. Min Act: -0.0000

Data Index: 1393367 (The Pile)

Max Activating Token Index: 752

Text #2

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.7390. Min Act: -0.0000

Data Index: 948937 (The Pile)

Max Activating Token Index: 70

Text #3

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.6795. Min Act: -0.0000

Data Index: 88666 (The Pile)

Max Activating Token Index: 49

Text #4

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.7371. Min Act: -0.0000

Data Index: 1041626 (The Pile)

Max Activating Token Index: 60

Text #5

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1372149 (The Pile)

Max Activating Token Index: 1011

Text #6

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.6469. Min Act: -0.0001

Data Index: 794019 (The Pile)

Max Activating Token Index: 944

Text #7

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.6863. Min Act: -0.0000

Data Index: 1609203 (The Pile)

Max Activating Token Index: 534

Text #8

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.6479. Min Act: -0.0000

Data Index: 116298 (The Pile)

Max Activating Token Index: 580

Text #9

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.6312. Min Act: -0.0000

Data Index: 493382 (The Pile)

Max Activating Token Index: 57

Text #10

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.5993. Min Act: -0.0000

Data Index: 1739132 (The Pile)

Max Activating Token Index: 705

Text #11

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.6619. Min Act: -0.0000

Data Index: 1716346 (The Pile)

Max Activating Token Index: 141

Text #12

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.6619. Min Act: -0.0000

Data Index: 1015661 (The Pile)

Max Activating Token Index: 371

Text #13

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.6315. Min Act: -0.0000

Data Index: 1147800 (The Pile)

Max Activating Token Index: 182

Text #14

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.6371. Min Act: -0.0000

Data Index: 869697 (The Pile)

Max Activating Token Index: 340

Text #15

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.6353. Min Act: -0.0000

Data Index: 1374758 (The Pile)

Max Activating Token Index: 935

Text #16

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.6051. Min Act: -0.0000

Data Index: 273477 (The Pile)

Max Activating Token Index: 793

Text #17

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.6392. Min Act: -0.0000

Data Index: 351056 (The Pile)

Max Activating Token Index: 839

Text #18

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1512907 (The Pile)

Max Activating Token Index: 693

Text #19

Max Range: 1.0322. Min Range: -1.0322

Max Act: 0.6323. Min Act: -0.0000

Data Index: 601902 (The Pile)

Max Activating Token Index: 114