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

Dataset: The Pile

Neuron 3730 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: 1.4233. Min Range: -1.4233

Max Act: 1.4233. Min Act: -0.0000

Data Index: 747602 (The Pile)

Max Activating Token Index: 316

Text #1

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.3375. Min Act: -0.0000

Data Index: 118478 (The Pile)

Max Activating Token Index: 180

Text #2

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.3034. Min Act: -0.0000

Data Index: 1879480 (The Pile)

Max Activating Token Index: 241

Text #3

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.2955. Min Act: -0.0000

Data Index: 478076 (The Pile)

Max Activating Token Index: 712

Text #4

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.2937. Min Act: -0.0000

Data Index: 685004 (The Pile)

Max Activating Token Index: 338

Text #5

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.2852. Min Act: -0.0000

Data Index: 894636 (The Pile)

Max Activating Token Index: 537

Text #6

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.2962. Min Act: -0.0000

Data Index: 1058021 (The Pile)

Max Activating Token Index: 149

Text #7

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.2464. Min Act: -0.0000

Data Index: 883974 (The Pile)

Max Activating Token Index: 572

Text #8

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.2118. Min Act: -0.0000

Data Index: 1479439 (The Pile)

Max Activating Token Index: 85

Text #9

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.2361. Min Act: -0.0000

Data Index: 1643425 (The Pile)

Max Activating Token Index: 138

Text #10

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.2416. Min Act: -0.0000

Data Index: 1818893 (The Pile)

Max Activating Token Index: 330

Text #11

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.2025. Min Act: -0.0000

Data Index: 1236761 (The Pile)

Max Activating Token Index: 561

Text #12

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.1839. Min Act: -0.0000

Data Index: 262592 (The Pile)

Max Activating Token Index: 982

Text #13

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.1638. Min Act: -0.0000

Data Index: 125459 (The Pile)

Max Activating Token Index: 1013

Text #14

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.2544. Min Act: -0.0000

Data Index: 1105273 (The Pile)

Max Activating Token Index: 306

Text #15

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.2199. Min Act: -0.0000

Data Index: 541506 (The Pile)

Max Activating Token Index: 82

Text #16

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.1707. Min Act: -0.0000

Data Index: 853731 (The Pile)

Max Activating Token Index: 492

Text #17

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.2080. Min Act: -0.0000

Data Index: 122945 (The Pile)

Max Activating Token Index: 329

Text #18

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.2388. Min Act: -0.0000

Data Index: 967033 (The Pile)

Max Activating Token Index: 974

Text #19

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.2002. Min Act: -0.0000

Data Index: 1344253 (The Pile)

Max Activating Token Index: 374