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

Dataset: The Pile

Neuron 1642 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1564735 (The Pile)

Max Activating Token Index: 812

Text #1

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1864766 (The Pile)

Max Activating Token Index: 422

Text #2

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4818. Min Act: -0.0000

Data Index: 1912463 (The Pile)

Max Activating Token Index: 854

Text #3

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.5576. Min Act: -0.0000

Data Index: 331098 (The Pile)

Max Activating Token Index: 703

Text #4

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.5059. Min Act: -0.0000

Data Index: 559635 (The Pile)

Max Activating Token Index: 429

Text #5

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4911. Min Act: -0.0000

Data Index: 1763878 (The Pile)

Max Activating Token Index: 871

Text #6

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4480. Min Act: -0.0000

Data Index: 474396 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1462171 (The Pile)

Max Activating Token Index: 927

Text #8

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1117087 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1691637 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3513. Min Act: -0.0000

Data Index: 1013759 (The Pile)

Max Activating Token Index: 921

Text #11

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3725. Min Act: -0.0000

Data Index: 268543 (The Pile)

Max Activating Token Index: 625

Text #12

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.4085. Min Act: -0.0000

Data Index: 1758262 (The Pile)

Max Activating Token Index: 733

Text #13

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3611. Min Act: -0.0000

Data Index: 208101 (The Pile)

Max Activating Token Index: 609

Text #14

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3650. Min Act: -0.0000

Data Index: 20494 (The Pile)

Max Activating Token Index: 25

Text #15

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3881. Min Act: -0.0000

Data Index: 946868 (The Pile)

Max Activating Token Index: 95

Text #16

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3619. Min Act: -0.0000

Data Index: 31360 (The Pile)

Max Activating Token Index: 382

Text #17

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3497. Min Act: -0.0000

Data Index: 670706 (The Pile)

Max Activating Token Index: 364

Text #18

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3620. Min Act: -0.0000

Data Index: 1059246 (The Pile)

Max Activating Token Index: 206

Text #19

Max Range: 0.5576. Min Range: -0.5576

Max Act: 0.3720. Min Act: -0.0000

Data Index: 754708 (The Pile)

Max Activating Token Index: 673