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

Dataset: The Pile

Neuron 3196 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.6444. Min Act: -0.0000

Data Index: 1831492 (The Pile)

Max Activating Token Index: 63

Text #1

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5900. Min Act: -0.0000

Data Index: 1785498 (The Pile)

Max Activating Token Index: 966

Text #2

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.6089. Min Act: -0.0000

Data Index: 1737278 (The Pile)

Max Activating Token Index: 831

Text #3

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5784. Min Act: -0.0000

Data Index: 1545679 (The Pile)

Max Activating Token Index: 157

Text #4

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5781. Min Act: -0.0000

Data Index: 256990 (The Pile)

Max Activating Token Index: 480

Text #5

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1738813 (The Pile)

Max Activating Token Index: 460

Text #6

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1320562 (The Pile)

Max Activating Token Index: 1012

Text #7

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5507. Min Act: 0.0000

Data Index: 1169056 (The Pile)

Max Activating Token Index: 731

Text #8

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5306. Min Act: -0.0000

Data Index: 949205 (The Pile)

Max Activating Token Index: 69

Text #9

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5305. Min Act: -0.0000

Data Index: 331877 (The Pile)

Max Activating Token Index: 434

Text #10

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5311. Min Act: -0.0000

Data Index: 1048734 (The Pile)

Max Activating Token Index: 50

Text #11

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1353554 (The Pile)

Max Activating Token Index: 669

Text #12

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5264. Min Act: 0.0000

Data Index: 1059162 (The Pile)

Max Activating Token Index: 397

Text #13

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1983215 (The Pile)

Max Activating Token Index: 703

Text #14

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5105. Min Act: -0.0000

Data Index: 699090 (The Pile)

Max Activating Token Index: 184

Text #15

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1001735 (The Pile)

Max Activating Token Index: 513

Text #16

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5088. Min Act: -0.0000

Data Index: 890125 (The Pile)

Max Activating Token Index: 834

Text #17

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1612412 (The Pile)

Max Activating Token Index: 22

Text #18

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5022. Min Act: 0.0000

Data Index: 1425221 (The Pile)

Max Activating Token Index: 659

Text #19

Max Range: 0.6444. Min Range: -0.6444

Max Act: 0.5025. Min Act: -0.0000

Data Index: 650107 (The Pile)

Max Activating Token Index: 633