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

Dataset: The Pile

Neuron 1097 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: 1.0105. Min Range: -1.0105

Max Act: 1.0105. Min Act: -0.0000

Data Index: 148629 (The Pile)

Max Activating Token Index: 200

Text #1

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.3259. Min Act: -0.0000

Data Index: 1293653 (The Pile)

Max Activating Token Index: 738

Text #2

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.2443. Min Act: -0.0000

Data Index: 922470 (The Pile)

Max Activating Token Index: 748

Text #3

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.2268. Min Act: -0.0000

Data Index: 820475 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1882543 (The Pile)

Max Activating Token Index: 719

Text #5

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.1435. Min Act: -0.0000

Data Index: 797395 (The Pile)

Max Activating Token Index: 887

Text #6

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.1613. Min Act: -0.0000

Data Index: 1037530 (The Pile)

Max Activating Token Index: 295

Text #7

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.1712. Min Act: -0.0000

Data Index: 186382 (The Pile)

Max Activating Token Index: 443

Text #8

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.1429. Min Act: -0.0000

Data Index: 503915 (The Pile)

Max Activating Token Index: 123

Text #9

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.1385. Min Act: -0.0000

Data Index: 699084 (The Pile)

Max Activating Token Index: 458

Text #10

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1670689 (The Pile)

Max Activating Token Index: 228

Text #11

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1975594 (The Pile)

Max Activating Token Index: 421

Text #12

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1187124 (The Pile)

Max Activating Token Index: 576

Text #13

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1987342 (The Pile)

Max Activating Token Index: 17

Text #14

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.1473. Min Act: -0.0000

Data Index: 653799 (The Pile)

Max Activating Token Index: 256

Text #15

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.1467. Min Act: -0.0000

Data Index: 355039 (The Pile)

Max Activating Token Index: 263

Text #16

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.1686. Min Act: -0.0000

Data Index: 1223907 (The Pile)

Max Activating Token Index: 548

Text #17

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.1367. Min Act: -0.0000

Data Index: 1675390 (The Pile)

Max Activating Token Index: 319

Text #18

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.1335. Min Act: -0.0000

Data Index: 1617141 (The Pile)

Max Activating Token Index: 689

Text #19

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.0716. Min Act: -0.0000

Data Index: 741859 (The Pile)

Max Activating Token Index: 600