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

Dataset: The Pile

Neuron 1102 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: 0.2956. Min Range: -0.2956

Max Act: 0.2777. Min Act: -0.0000

Data Index: 706047 (The Pile)

Max Activating Token Index: 472

Text #1

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1471709 (The Pile)

Max Activating Token Index: 732

Text #2

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2956. Min Act: -0.0000

Data Index: 658078 (The Pile)

Max Activating Token Index: 711

Text #3

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2610. Min Act: -0.0000

Data Index: 1233270 (The Pile)

Max Activating Token Index: 312

Text #4

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2743. Min Act: -0.0000

Data Index: 1634684 (The Pile)

Max Activating Token Index: 799

Text #5

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2380. Min Act: -0.0000

Data Index: 1331667 (The Pile)

Max Activating Token Index: 288

Text #6

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2403. Min Act: -0.0000

Data Index: 1818243 (The Pile)

Max Activating Token Index: 456

Text #7

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2455. Min Act: -0.0000

Data Index: 1830000 (The Pile)

Max Activating Token Index: 437

Text #8

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2334. Min Act: -0.0000

Data Index: 183358 (The Pile)

Max Activating Token Index: 230

Text #9

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2372. Min Act: -0.0000

Data Index: 483557 (The Pile)

Max Activating Token Index: 389

Text #10

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1679095 (The Pile)

Max Activating Token Index: 669

Text #11

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1982315 (The Pile)

Max Activating Token Index: 359

Text #12

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2306. Min Act: -0.0000

Data Index: 892318 (The Pile)

Max Activating Token Index: 580

Text #13

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1182158 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2388. Min Act: -0.0000

Data Index: 113398 (The Pile)

Max Activating Token Index: 525

Text #15

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2428. Min Act: -0.0000

Data Index: 1191785 (The Pile)

Max Activating Token Index: 897

Text #16

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1479419 (The Pile)

Max Activating Token Index: 391

Text #17

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2057. Min Act: -0.0000

Data Index: 547616 (The Pile)

Max Activating Token Index: 98

Text #18

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2308. Min Act: -0.0000

Data Index: 141948 (The Pile)

Max Activating Token Index: 789

Text #19

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2308. Min Act: -0.0000

Data Index: 626904 (The Pile)

Max Activating Token Index: 680