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

Dataset: The Pile

Neuron 1468 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7261. Min Range: -3.7261

Max Act: 3.7261. Min Act: -0.0000

Data Index: 1845193 (The Pile)

Max Activating Token Index: 276

Text #1

Max Range: 3.7261. Min Range: -3.7261

Max Act: 3.4728. Min Act: 0.0000

Data Index: 38810 (The Pile)

Max Activating Token Index: 281

Text #2

Max Range: 3.7261. Min Range: -3.7261

Max Act: 3.2967. Min Act: -0.0000

Data Index: 1784154 (The Pile)

Max Activating Token Index: 33

Text #3

Max Range: 3.7261. Min Range: -3.7261

Max Act: 3.5359. Min Act: -0.0000

Data Index: 526015 (The Pile)

Max Activating Token Index: 356

Text #4

Max Range: 3.7261. Min Range: -3.7261

Max Act: 2.6193. Min Act: -0.0000

Data Index: 605216 (The Pile)

Max Activating Token Index: 699

Text #5

Max Range: 3.7261. Min Range: -3.7261

Max Act: 3.5266. Min Act: -0.0000

Data Index: 823111 (The Pile)

Max Activating Token Index: 74

Text #6

Max Range: 3.7261. Min Range: -3.7261

Max Act: 3.2069. Min Act: 0.0000

Data Index: 454502 (The Pile)

Max Activating Token Index: 886

Text #7

Max Range: 3.7261. Min Range: -3.7261

Max Act: 3.2889. Min Act: -0.0000

Data Index: 1238604 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 3.7261. Min Range: -3.7261

Max Act: 3.1514. Min Act: 0.0000

Data Index: 757550 (The Pile)

Max Activating Token Index: 544

Text #9

Max Range: 3.7261. Min Range: -3.7261

Max Act: 3.2853. Min Act: -0.0000

Data Index: 1269569 (The Pile)

Max Activating Token Index: 670

Text #10

Max Range: 3.7261. Min Range: -3.7261

Max Act: 3.2362. Min Act: -0.0000

Data Index: 1466321 (The Pile)

Max Activating Token Index: 392

Text #11

Max Range: 3.7261. Min Range: -3.7261

Max Act: 3.2346. Min Act: -0.0000

Data Index: 726915 (The Pile)

Max Activating Token Index: 397

Text #12

Max Range: 3.7261. Min Range: -3.7261

Max Act: 3.0721. Min Act: -0.0000

Data Index: 221288 (The Pile)

Max Activating Token Index: 409

Text #13

Max Range: 3.7261. Min Range: -3.7261

Max Act: 3.2113. Min Act: -0.0000

Data Index: 886490 (The Pile)

Max Activating Token Index: 353

Text #14

Max Range: 3.7261. Min Range: -3.7261

Max Act: 2.2597. Min Act: -0.0000

Data Index: 685953 (The Pile)

Max Activating Token Index: 622

Text #15

Max Range: 3.7261. Min Range: -3.7261

Max Act: 3.1586. Min Act: -0.0000

Data Index: 1514303 (The Pile)

Max Activating Token Index: 416

Text #16

Max Range: 3.7261. Min Range: -3.7261

Max Act: 2.8528. Min Act: -0.0000

Data Index: 311646 (The Pile)

Max Activating Token Index: 572

Text #17

Max Range: 3.7261. Min Range: -3.7261

Max Act: 2.8528. Min Act: -0.0000

Data Index: 147948 (The Pile)

Max Activating Token Index: 572

Text #18

Max Range: 3.7261. Min Range: -3.7261

Max Act: 3.0303. Min Act: -0.0000

Data Index: 1262303 (The Pile)

Max Activating Token Index: 269

Text #19

Max Range: 3.7261. Min Range: -3.7261

Max Act: 3.1180. Min Act: -0.0000

Data Index: 983672 (The Pile)

Max Activating Token Index: 79