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

Dataset: The Pile

Neuron 136 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.5951. Min Act: -0.0000

Data Index: 1696759 (The Pile)

Max Activating Token Index: 130

Text #1

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.3350. Min Act: -0.0000

Data Index: 362667 (The Pile)

Max Activating Token Index: 434

Text #2

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.1355. Min Act: -0.0000

Data Index: 1802751 (The Pile)

Max Activating Token Index: 544

Text #3

Max Range: 5.5951. Min Range: -5.5951

Max Act: 4.9396. Min Act: -0.0000

Data Index: 1412241 (The Pile)

Max Activating Token Index: 839

Text #4

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.4332. Min Act: -0.0000

Data Index: 143627 (The Pile)

Max Activating Token Index: 227

Text #5

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.1448. Min Act: -0.0000

Data Index: 1939121 (The Pile)

Max Activating Token Index: 502

Text #6

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.1055. Min Act: -0.0000

Data Index: 1230824 (The Pile)

Max Activating Token Index: 409

Text #7

Max Range: 5.5951. Min Range: -5.5951

Max Act: 4.6121. Min Act: -0.0000

Data Index: 201361 (The Pile)

Max Activating Token Index: 328

Text #8

Max Range: 5.5951. Min Range: -5.5951

Max Act: 4.8822. Min Act: -0.0000

Data Index: 1294282 (The Pile)

Max Activating Token Index: 706

Text #9

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.0774. Min Act: -0.0000

Data Index: 1265334 (The Pile)

Max Activating Token Index: 357

Text #10

Max Range: 5.5951. Min Range: -5.5951

Max Act: 4.6843. Min Act: -0.0000

Data Index: 423884 (The Pile)

Max Activating Token Index: 740

Text #11

Max Range: 5.5951. Min Range: -5.5951

Max Act: 4.8552. Min Act: -0.0000

Data Index: 389332 (The Pile)

Max Activating Token Index: 914

Text #12

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.0046. Min Act: -0.0000

Data Index: 749213 (The Pile)

Max Activating Token Index: 929

Text #13

Max Range: 5.5951. Min Range: -5.5951

Max Act: 4.5410. Min Act: -0.0000

Data Index: 1341791 (The Pile)

Max Activating Token Index: 313

Text #14

Max Range: 5.5951. Min Range: -5.5951

Max Act: 4.4079. Min Act: -0.0000

Data Index: 1203542 (The Pile)

Max Activating Token Index: 983

Text #15

Max Range: 5.5951. Min Range: -5.5951

Max Act: 4.3942. Min Act: -0.0000

Data Index: 1987551 (The Pile)

Max Activating Token Index: 500

Text #16

Max Range: 5.5951. Min Range: -5.5951

Max Act: 4.5298. Min Act: -0.0000

Data Index: 842342 (The Pile)

Max Activating Token Index: 322

Text #17

Max Range: 5.5951. Min Range: -5.5951

Max Act: 4.8699. Min Act: -0.0000

Data Index: 1394689 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 5.5951. Min Range: -5.5951

Max Act: 4.4163. Min Act: -0.0000

Data Index: 560663 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 5.5951. Min Range: -5.5951

Max Act: 4.3996. Min Act: -0.0000

Data Index: 912485 (The Pile)

Max Activating Token Index: 574