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

Dataset: The Pile

Neuron 2139 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.8154. Min Act: -0.0000

Data Index: 639340 (The Pile)

Max Activating Token Index: 290

Text #1

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.9261. Min Act: -0.0000

Data Index: 1237786 (The Pile)

Max Activating Token Index: 816

Text #2

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.8668. Min Act: -0.0000

Data Index: 1842433 (The Pile)

Max Activating Token Index: 723

Text #3

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.5296. Min Act: -0.0000

Data Index: 613687 (The Pile)

Max Activating Token Index: 332

Text #4

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.4415. Min Act: -0.0000

Data Index: 940494 (The Pile)

Max Activating Token Index: 139

Text #5

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.5457. Min Act: -0.0000

Data Index: 1640842 (The Pile)

Max Activating Token Index: 472

Text #6

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.3678. Min Act: -0.0000

Data Index: 1208845 (The Pile)

Max Activating Token Index: 649

Text #7

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.3470. Min Act: -0.0000

Data Index: 934399 (The Pile)

Max Activating Token Index: 112

Text #8

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.3444. Min Act: -0.0000

Data Index: 1802850 (The Pile)

Max Activating Token Index: 641

Text #9

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.1211. Min Act: -0.0000

Data Index: 678127 (The Pile)

Max Activating Token Index: 940

Text #10

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.3610. Min Act: -0.0000

Data Index: 839344 (The Pile)

Max Activating Token Index: 130

Text #11

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.1872. Min Act: -0.0000

Data Index: 643901 (The Pile)

Max Activating Token Index: 687

Text #12

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.1974. Min Act: -0.0000

Data Index: 1082183 (The Pile)

Max Activating Token Index: 66

Text #13

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.3162. Min Act: -0.0000

Data Index: 1183644 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 3.9261. Min Range: -3.9261

Max Act: 2.9758. Min Act: -0.0000

Data Index: 1766838 (The Pile)

Max Activating Token Index: 190

Text #15

Max Range: 3.9261. Min Range: -3.9261

Max Act: 2.8315. Min Act: -0.0000

Data Index: 1933769 (The Pile)

Max Activating Token Index: 706

Text #16

Max Range: 3.9261. Min Range: -3.9261

Max Act: 2.9458. Min Act: -0.0000

Data Index: 753336 (The Pile)

Max Activating Token Index: 25

Text #17

Max Range: 3.9261. Min Range: -3.9261

Max Act: 2.9080. Min Act: -0.0000

Data Index: 325309 (The Pile)

Max Activating Token Index: 217

Text #18

Max Range: 3.9261. Min Range: -3.9261

Max Act: 3.0140. Min Act: -0.0000

Data Index: 982596 (The Pile)

Max Activating Token Index: 774

Text #19

Max Range: 3.9261. Min Range: -3.9261

Max Act: 2.9882. Min Act: -0.0000

Data Index: 1668022 (The Pile)

Max Activating Token Index: 431