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

Dataset: The Pile

Neuron 4384 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9256. Min Range: -5.9256

Max Act: 5.5450. Min Act: -0.0000

Data Index: 53927 (The Pile)

Max Activating Token Index: 554

Text #1

Max Range: 5.9256. Min Range: -5.9256

Max Act: 5.9256. Min Act: -0.0000

Data Index: 456222 (The Pile)

Max Activating Token Index: 970

Text #2

Max Range: 5.9256. Min Range: -5.9256

Max Act: 5.2110. Min Act: -0.0000

Data Index: 1322046 (The Pile)

Max Activating Token Index: 698

Text #3

Max Range: 5.9256. Min Range: -5.9256

Max Act: 5.5559. Min Act: -0.0000

Data Index: 1743224 (The Pile)

Max Activating Token Index: 544

Text #4

Max Range: 5.9256. Min Range: -5.9256

Max Act: 5.2897. Min Act: -0.0000

Data Index: 1329270 (The Pile)

Max Activating Token Index: 148

Text #5

Max Range: 5.9256. Min Range: -5.9256

Max Act: 5.6165. Min Act: -0.0000

Data Index: 1927097 (The Pile)

Max Activating Token Index: 617

Text #6

Max Range: 5.9256. Min Range: -5.9256

Max Act: 5.0906. Min Act: -0.0000

Data Index: 1237901 (The Pile)

Max Activating Token Index: 441

Text #7

Max Range: 5.9256. Min Range: -5.9256

Max Act: 4.7335. Min Act: -0.0000

Data Index: 240704 (The Pile)

Max Activating Token Index: 368

Text #8

Max Range: 5.9256. Min Range: -5.9256

Max Act: 4.7268. Min Act: -0.0000

Data Index: 1448772 (The Pile)

Max Activating Token Index: 593

Text #9

Max Range: 5.9256. Min Range: -5.9256

Max Act: 4.6942. Min Act: -0.0000

Data Index: 1454428 (The Pile)

Max Activating Token Index: 537

Text #10

Max Range: 5.9256. Min Range: -5.9256

Max Act: 5.1637. Min Act: -0.0000

Data Index: 31737 (The Pile)

Max Activating Token Index: 555

Text #11

Max Range: 5.9256. Min Range: -5.9256

Max Act: 4.6830. Min Act: -0.0000

Data Index: 430578 (The Pile)

Max Activating Token Index: 858

Text #12

Max Range: 5.9256. Min Range: -5.9256

Max Act: 4.3330. Min Act: -0.0000

Data Index: 170854 (The Pile)

Max Activating Token Index: 54

Text #13

Max Range: 5.9256. Min Range: -5.9256

Max Act: 4.9079. Min Act: -0.0000

Data Index: 812779 (The Pile)

Max Activating Token Index: 206

Text #14

Max Range: 5.9256. Min Range: -5.9256

Max Act: 4.6725. Min Act: -0.0000

Data Index: 1522324 (The Pile)

Max Activating Token Index: 206

Text #15

Max Range: 5.9256. Min Range: -5.9256

Max Act: 4.4620. Min Act: -0.0000

Data Index: 1148372 (The Pile)

Max Activating Token Index: 862

Text #16

Max Range: 5.9256. Min Range: -5.9256

Max Act: 4.6478. Min Act: -0.0000

Data Index: 1926089 (The Pile)

Max Activating Token Index: 728

Text #17

Max Range: 5.9256. Min Range: -5.9256

Max Act: 4.8293. Min Act: -0.0000

Data Index: 1015086 (The Pile)

Max Activating Token Index: 239

Text #18

Max Range: 5.9256. Min Range: -5.9256

Max Act: 4.4346. Min Act: -0.0000

Data Index: 768959 (The Pile)

Max Activating Token Index: 288

Text #19

Max Range: 5.9256. Min Range: -5.9256

Max Act: 4.4279. Min Act: -0.0000

Data Index: 933996 (The Pile)

Max Activating Token Index: 15