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

Dataset: The Pile

Neuron 2431 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.8280. Min Act: -0.0000

Data Index: 617002 (The Pile)

Max Activating Token Index: 542

Text #1

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.7318. Min Act: -0.0000

Data Index: 1142440 (The Pile)

Max Activating Token Index: 466

Text #2

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.7001. Min Act: -0.0000

Data Index: 1914965 (The Pile)

Max Activating Token Index: 217

Text #3

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.5982. Min Act: -0.0000

Data Index: 644519 (The Pile)

Max Activating Token Index: 202

Text #4

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.5109. Min Act: -0.0000

Data Index: 260525 (The Pile)

Max Activating Token Index: 728

Text #5

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.4441. Min Act: -0.0000

Data Index: 1765642 (The Pile)

Max Activating Token Index: 580

Text #6

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.2612. Min Act: -0.0000

Data Index: 403126 (The Pile)

Max Activating Token Index: 910

Text #7

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.2824. Min Act: -0.0000

Data Index: 754040 (The Pile)

Max Activating Token Index: 510

Text #8

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.2577. Min Act: -0.0000

Data Index: 897735 (The Pile)

Max Activating Token Index: 985

Text #9

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.2867. Min Act: -0.0000

Data Index: 1607305 (The Pile)

Max Activating Token Index: 883

Text #10

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.1509. Min Act: -0.0000

Data Index: 1888679 (The Pile)

Max Activating Token Index: 264

Text #11

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.3051. Min Act: -0.0000

Data Index: 1617917 (The Pile)

Max Activating Token Index: 613

Text #12

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.1288. Min Act: -0.0000

Data Index: 540768 (The Pile)

Max Activating Token Index: 658

Text #13

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.0460. Min Act: -0.0000

Data Index: 1476177 (The Pile)

Max Activating Token Index: 580

Text #14

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.0473. Min Act: -0.0000

Data Index: 1850807 (The Pile)

Max Activating Token Index: 214

Text #15

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.1026. Min Act: -0.0000

Data Index: 303737 (The Pile)

Max Activating Token Index: 495

Text #16

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.2327. Min Act: -0.0000

Data Index: 1807167 (The Pile)

Max Activating Token Index: 43

Text #17

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.0844. Min Act: -0.0000

Data Index: 1202944 (The Pile)

Max Activating Token Index: 674

Text #18

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.0584. Min Act: -0.0000

Data Index: 1573030 (The Pile)

Max Activating Token Index: 579

Text #19

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.0136. Min Act: -0.0000

Data Index: 804115 (The Pile)

Max Activating Token Index: 366