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

Dataset: The Pile

Neuron 1909 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.8266. Min Act: -0.0000

Data Index: 1254877 (The Pile)

Max Activating Token Index: 857

Text #1

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6890. Min Act: -0.0000

Data Index: 1517421 (The Pile)

Max Activating Token Index: 776

Text #2

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6147. Min Act: -0.0000

Data Index: 37076 (The Pile)

Max Activating Token Index: 782

Text #3

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.4946. Min Act: -0.0000

Data Index: 1033324 (The Pile)

Max Activating Token Index: 255

Text #4

Max Range: 3.8268. Min Range: -3.8268

Max Act: 2.9950. Min Act: -0.0000

Data Index: 514306 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.8268. Min Act: -0.0000

Data Index: 462275 (The Pile)

Max Activating Token Index: 455

Text #6

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.5142. Min Act: -0.0000

Data Index: 1400786 (The Pile)

Max Activating Token Index: 217

Text #7

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.4422. Min Act: -0.0000

Data Index: 1866619 (The Pile)

Max Activating Token Index: 903

Text #8

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.0518. Min Act: -0.0000

Data Index: 1561269 (The Pile)

Max Activating Token Index: 33

Text #9

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.0902. Min Act: -0.0000

Data Index: 992350 (The Pile)

Max Activating Token Index: 968

Text #10

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.4069. Min Act: -0.0000

Data Index: 1149499 (The Pile)

Max Activating Token Index: 344

Text #11

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.2208. Min Act: -0.0000

Data Index: 443204 (The Pile)

Max Activating Token Index: 905

Text #12

Max Range: 3.8268. Min Range: -3.8268

Max Act: 2.7503. Min Act: -0.0000

Data Index: 701210 (The Pile)

Max Activating Token Index: 1022

Text #13

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.1773. Min Act: -0.0000

Data Index: 1255479 (The Pile)

Max Activating Token Index: 882

Text #14

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.0544. Min Act: -0.0000

Data Index: 1804937 (The Pile)

Max Activating Token Index: 985

Text #15

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.2255. Min Act: -0.0000

Data Index: 1467378 (The Pile)

Max Activating Token Index: 503

Text #16

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.1870. Min Act: -0.0000

Data Index: 1465501 (The Pile)

Max Activating Token Index: 606

Text #17

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.2488. Min Act: -0.0000

Data Index: 1220133 (The Pile)

Max Activating Token Index: 585

Text #18

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.7192. Min Act: -0.0000

Data Index: 777020 (The Pile)

Max Activating Token Index: 692

Text #19

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.1450. Min Act: -0.0000

Data Index: 975557 (The Pile)

Max Activating Token Index: 390