Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1065 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.4491. Min Act: -0.0000

Data Index: 139250 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.3790. Min Act: -0.0000

Data Index: 399959 (The Pile)

Max Activating Token Index: 386

Text #2

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.3830. Min Act: -0.0000

Data Index: 213453 (The Pile)

Max Activating Token Index: 664

Text #3

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.3050. Min Act: -0.0000

Data Index: 1457084 (The Pile)

Max Activating Token Index: 722

Text #4

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2809. Min Act: -0.0000

Data Index: 898042 (The Pile)

Max Activating Token Index: 393

Text #5

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2965. Min Act: -0.0000

Data Index: 395801 (The Pile)

Max Activating Token Index: 824

Text #6

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2781. Min Act: -0.0000

Data Index: 1811891 (The Pile)

Max Activating Token Index: 568

Text #7

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2698. Min Act: -0.0001

Data Index: 1575858 (The Pile)

Max Activating Token Index: 600

Text #8

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2484. Min Act: -0.0000

Data Index: 376159 (The Pile)

Max Activating Token Index: 718

Text #9

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2495. Min Act: -0.0000

Data Index: 1335701 (The Pile)

Max Activating Token Index: 213

Text #10

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2540. Min Act: -0.0000

Data Index: 745787 (The Pile)

Max Activating Token Index: 745

Text #11

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2612. Min Act: -0.0000

Data Index: 591547 (The Pile)

Max Activating Token Index: 476

Text #12

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2651. Min Act: -0.0000

Data Index: 621407 (The Pile)

Max Activating Token Index: 987

Text #13

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2378. Min Act: -0.0000

Data Index: 1171110 (The Pile)

Max Activating Token Index: 410

Text #14

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2357. Min Act: -0.0000

Data Index: 128341 (The Pile)

Max Activating Token Index: 281

Text #15

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2436. Min Act: -0.0001

Data Index: 759611 (The Pile)

Max Activating Token Index: 782

Text #16

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2409. Min Act: -0.0000

Data Index: 1403559 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1473090 (The Pile)

Max Activating Token Index: 477

Text #18

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2455. Min Act: -0.0000

Data Index: 950669 (The Pile)

Max Activating Token Index: 367

Text #19

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2328. Min Act: -0.0000

Data Index: 1184377 (The Pile)

Max Activating Token Index: 836