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

Dataset: The Pile

Neuron 1180 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.8084. Min Act: -0.0000

Data Index: 485378 (The Pile)

Max Activating Token Index: 894

Text #1

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.7088. Min Act: -0.0000

Data Index: 1012791 (The Pile)

Max Activating Token Index: 373

Text #2

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1809. Min Act: -0.0000

Data Index: 1725274 (The Pile)

Max Activating Token Index: 870

Text #3

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2468. Min Act: -0.0000

Data Index: 1209955 (The Pile)

Max Activating Token Index: 526

Text #4

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2377. Min Act: -0.0000

Data Index: 811215 (The Pile)

Max Activating Token Index: 937

Text #5

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.4910. Min Act: -0.0000

Data Index: 1623351 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2653. Min Act: -0.0000

Data Index: 45811 (The Pile)

Max Activating Token Index: 540

Text #7

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2739. Min Act: -0.0000

Data Index: 1024368 (The Pile)

Max Activating Token Index: 16

Text #8

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2411. Min Act: -0.0000

Data Index: 1463923 (The Pile)

Max Activating Token Index: 540

Text #9

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2424. Min Act: -0.0000

Data Index: 68961 (The Pile)

Max Activating Token Index: 585

Text #10

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1715. Min Act: -0.0000

Data Index: 1000681 (The Pile)

Max Activating Token Index: 1015

Text #11

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2302. Min Act: -0.0000

Data Index: 1113692 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2709. Min Act: -0.0000

Data Index: 1902019 (The Pile)

Max Activating Token Index: 333

Text #13

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1147. Min Act: -0.0000

Data Index: 907084 (The Pile)

Max Activating Token Index: 160

Text #14

Max Range: 1.8084. Min Range: -1.8084

Max Act: 0.9760. Min Act: -0.0000

Data Index: 180086 (The Pile)

Max Activating Token Index: 570

Text #15

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2488. Min Act: -0.0000

Data Index: 714423 (The Pile)

Max Activating Token Index: 27

Text #16

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2134. Min Act: -0.0000

Data Index: 1115537 (The Pile)

Max Activating Token Index: 616

Text #17

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1415. Min Act: -0.0000

Data Index: 1174049 (The Pile)

Max Activating Token Index: 279

Text #18

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1398. Min Act: -0.0000

Data Index: 111661 (The Pile)

Max Activating Token Index: 295

Text #19

Max Range: 1.8084. Min Range: -1.8084

Max Act: 0.9424. Min Act: -0.0000

Data Index: 1866752 (The Pile)

Max Activating Token Index: 559