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

Dataset: The Pile

Neuron 188 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: 0.9348. Min Range: -0.9348

Max Act: 0.9215. Min Act: -0.0000

Data Index: 503107 (The Pile)

Max Activating Token Index: 245

Text #1

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1631432 (The Pile)

Max Activating Token Index: 872

Text #2

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.9348. Min Act: -0.0000

Data Index: 1143090 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.8642. Min Act: -0.0000

Data Index: 539258 (The Pile)

Max Activating Token Index: 639

Text #4

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7927. Min Act: -0.0000

Data Index: 251322 (The Pile)

Max Activating Token Index: 832

Text #5

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7923. Min Act: -0.0000

Data Index: 1613346 (The Pile)

Max Activating Token Index: 163

Text #6

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7929. Min Act: -0.0000

Data Index: 1293565 (The Pile)

Max Activating Token Index: 324

Text #7

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7755. Min Act: -0.0000

Data Index: 365037 (The Pile)

Max Activating Token Index: 654

Text #8

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7511. Min Act: -0.0000

Data Index: 1672126 (The Pile)

Max Activating Token Index: 815

Text #9

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7122. Min Act: -0.0000

Data Index: 960959 (The Pile)

Max Activating Token Index: 388

Text #10

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7358. Min Act: -0.0000

Data Index: 52720 (The Pile)

Max Activating Token Index: 919

Text #11

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6650. Min Act: -0.0000

Data Index: 965096 (The Pile)

Max Activating Token Index: 550

Text #12

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7091. Min Act: -0.0000

Data Index: 119344 (The Pile)

Max Activating Token Index: 855

Text #13

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7038. Min Act: -0.0000

Data Index: 1332620 (The Pile)

Max Activating Token Index: 165

Text #14

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6516. Min Act: -0.0000

Data Index: 1297817 (The Pile)

Max Activating Token Index: 428

Text #15

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6718. Min Act: -0.0000

Data Index: 944872 (The Pile)

Max Activating Token Index: 862

Text #16

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1766917 (The Pile)

Max Activating Token Index: 373

Text #17

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6913. Min Act: -0.0000

Data Index: 142265 (The Pile)

Max Activating Token Index: 134

Text #18

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1862880 (The Pile)

Max Activating Token Index: 158

Text #19

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1842889 (The Pile)

Max Activating Token Index: 637