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

Dataset: The Pile

Neuron 4054 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: 3.3105. Min Range: -3.3105

Max Act: 3.2101. Min Act: -0.0000

Data Index: 1964037 (The Pile)

Max Activating Token Index: 804

Text #1

Max Range: 3.3105. Min Range: -3.3105

Max Act: 3.3105. Min Act: -0.0000

Data Index: 527253 (The Pile)

Max Activating Token Index: 736

Text #2

Max Range: 3.3105. Min Range: -3.3105

Max Act: 2.9361. Min Act: -0.0000

Data Index: 1038020 (The Pile)

Max Activating Token Index: 622

Text #3

Max Range: 3.3105. Min Range: -3.3105

Max Act: 2.4161. Min Act: -0.0000

Data Index: 593232 (The Pile)

Max Activating Token Index: 670

Text #4

Max Range: 3.3105. Min Range: -3.3105

Max Act: 2.5876. Min Act: -0.0000

Data Index: 213088 (The Pile)

Max Activating Token Index: 77

Text #5

Max Range: 3.3105. Min Range: -3.3105

Max Act: 2.6993. Min Act: -0.0000

Data Index: 242311 (The Pile)

Max Activating Token Index: 505

Text #6

Max Range: 3.3105. Min Range: -3.3105

Max Act: 2.2499. Min Act: 0.0000

Data Index: 1791974 (The Pile)

Max Activating Token Index: 78

Text #7

Max Range: 3.3105. Min Range: -3.3105

Max Act: 2.2877. Min Act: -0.0000

Data Index: 875568 (The Pile)

Max Activating Token Index: 181

Text #8

Max Range: 3.3105. Min Range: -3.3105

Max Act: 2.0909. Min Act: 0.0001

Data Index: 1412659 (The Pile)

Max Activating Token Index: 596

Text #9

Max Range: 3.3105. Min Range: -3.3105

Max Act: 2.1580. Min Act: -0.0000

Data Index: 1641282 (The Pile)

Max Activating Token Index: 495

Text #10

Max Range: 3.3105. Min Range: -3.3105

Max Act: 2.1274. Min Act: 0.0000

Data Index: 224880 (The Pile)

Max Activating Token Index: 42

Text #11

Max Range: 3.3105. Min Range: -3.3105

Max Act: 2.2914. Min Act: -0.0000

Data Index: 423505 (The Pile)

Max Activating Token Index: 415

Text #12

Max Range: 3.3105. Min Range: -3.3105

Max Act: 2.2090. Min Act: 0.0000

Data Index: 1465607 (The Pile)

Max Activating Token Index: 383

Text #13

Max Range: 3.3105. Min Range: -3.3105

Max Act: 2.1091. Min Act: -0.0000

Data Index: 1683872 (The Pile)

Max Activating Token Index: 195

Text #14

Max Range: 3.3105. Min Range: -3.3105

Max Act: 2.0784. Min Act: -0.0000

Data Index: 394728 (The Pile)

Max Activating Token Index: 372

Text #15

Max Range: 3.3105. Min Range: -3.3105

Max Act: 1.9020. Min Act: 0.0000

Data Index: 1953057 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 3.3105. Min Range: -3.3105

Max Act: 1.8528. Min Act: 0.0000

Data Index: 1125332 (The Pile)

Max Activating Token Index: 651

Text #17

Max Range: 3.3105. Min Range: -3.3105

Max Act: 1.8333. Min Act: -0.0000

Data Index: 1830043 (The Pile)

Max Activating Token Index: 631

Text #18

Max Range: 3.3105. Min Range: -3.3105

Max Act: 1.9151. Min Act: 0.0000

Data Index: 1375181 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 3.3105. Min Range: -3.3105

Max Act: 1.7768. Min Act: 0.0000

Data Index: 1156360 (The Pile)

Max Activating Token Index: 26