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

Dataset: The Pile

Neuron 2579 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.5394. Min Act: -0.0000

Data Index: 1195900 (The Pile)

Max Activating Token Index: 823

Text #1

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.5815. Min Act: -0.0000

Data Index: 338611 (The Pile)

Max Activating Token Index: 74

Text #2

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.5220. Min Act: -0.0000

Data Index: 474020 (The Pile)

Max Activating Token Index: 366

Text #3

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.5305. Min Act: -0.0000

Data Index: 264648 (The Pile)

Max Activating Token Index: 730

Text #4

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.5554. Min Act: -0.0000

Data Index: 690793 (The Pile)

Max Activating Token Index: 705

Text #5

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.4409. Min Act: -0.0000

Data Index: 1772433 (The Pile)

Max Activating Token Index: 876

Text #6

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.4841. Min Act: -0.0000

Data Index: 945102 (The Pile)

Max Activating Token Index: 678

Text #7

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.3862. Min Act: -0.0000

Data Index: 1090606 (The Pile)

Max Activating Token Index: 295

Text #8

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.3879. Min Act: -0.0000

Data Index: 1747995 (The Pile)

Max Activating Token Index: 964

Text #9

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.3805. Min Act: -0.0000

Data Index: 1393296 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.4136. Min Act: -0.0000

Data Index: 987035 (The Pile)

Max Activating Token Index: 916

Text #11

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.4518. Min Act: -0.0000

Data Index: 1436147 (The Pile)

Max Activating Token Index: 681

Text #12

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.4679. Min Act: -0.0000

Data Index: 1182224 (The Pile)

Max Activating Token Index: 399

Text #13

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.3659. Min Act: -0.0000

Data Index: 1010040 (The Pile)

Max Activating Token Index: 331

Text #14

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.4745. Min Act: -0.0000

Data Index: 221640 (The Pile)

Max Activating Token Index: 829

Text #15

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.3917. Min Act: -0.0000

Data Index: 695074 (The Pile)

Max Activating Token Index: 901

Text #16

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.4161. Min Act: -0.0000

Data Index: 140822 (The Pile)

Max Activating Token Index: 180

Text #17

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.3737. Min Act: -0.0000

Data Index: 1952660 (The Pile)

Max Activating Token Index: 992

Text #18

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.3715. Min Act: -0.0000

Data Index: 1672599 (The Pile)

Max Activating Token Index: 692

Text #19

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.3723. Min Act: -0.0000

Data Index: 1633949 (The Pile)

Max Activating Token Index: 404