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

Dataset: The Pile

Neuron 4539 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.0276. Min Act: -0.0000

Data Index: 891045 (The Pile)

Max Activating Token Index: 273

Text #1

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.0247. Min Act: -0.0000

Data Index: 1361276 (The Pile)

Max Activating Token Index: 240

Text #2

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.3337. Min Act: -0.0000

Data Index: 481260 (The Pile)

Max Activating Token Index: 210

Text #3

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.8841. Min Act: -0.0000

Data Index: 1331256 (The Pile)

Max Activating Token Index: 676

Text #4

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.8748. Min Act: -0.0000

Data Index: 886538 (The Pile)

Max Activating Token Index: 774

Text #5

Max Range: 3.3337. Min Range: -3.3337

Max Act: 3.0990. Min Act: -0.0000

Data Index: 1317142 (The Pile)

Max Activating Token Index: 279

Text #6

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.6147. Min Act: -0.0000

Data Index: 757069 (The Pile)

Max Activating Token Index: 968

Text #7

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.9084. Min Act: -0.0000

Data Index: 991808 (The Pile)

Max Activating Token Index: 775

Text #8

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.7226. Min Act: -0.0000

Data Index: 1986708 (The Pile)

Max Activating Token Index: 391

Text #9

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.7958. Min Act: -0.0000

Data Index: 1660026 (The Pile)

Max Activating Token Index: 389

Text #10

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.5641. Min Act: -0.0000

Data Index: 1209172 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.7751. Min Act: -0.0000

Data Index: 1091396 (The Pile)

Max Activating Token Index: 339

Text #12

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.7789. Min Act: -0.0000

Data Index: 531554 (The Pile)

Max Activating Token Index: 501

Text #13

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.7634. Min Act: -0.0000

Data Index: 52494 (The Pile)

Max Activating Token Index: 785

Text #14

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.6453. Min Act: -0.0000

Data Index: 1766955 (The Pile)

Max Activating Token Index: 758

Text #15

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.8718. Min Act: -0.0000

Data Index: 992335 (The Pile)

Max Activating Token Index: 430

Text #16

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.6806. Min Act: -0.0000

Data Index: 563074 (The Pile)

Max Activating Token Index: 314

Text #17

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.6013. Min Act: -0.0000

Data Index: 804725 (The Pile)

Max Activating Token Index: 500

Text #18

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.3045. Min Act: -0.0000

Data Index: 1414151 (The Pile)

Max Activating Token Index: 929

Text #19

Max Range: 3.3337. Min Range: -3.3337

Max Act: 2.4470. Min Act: -0.0000

Data Index: 1352325 (The Pile)

Max Activating Token Index: 777