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

Dataset: The Pile

Neuron 3401 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.4303. Min Act: -0.0000

Data Index: 722016 (The Pile)

Max Activating Token Index: 589

Text #1

Max Range: 5.4303. Min Range: -5.4303

Max Act: 4.9764. Min Act: -0.0000

Data Index: 567591 (The Pile)

Max Activating Token Index: 630

Text #2

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.1024. Min Act: -0.0000

Data Index: 832814 (The Pile)

Max Activating Token Index: 520

Text #3

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.0122. Min Act: -0.0000

Data Index: 360670 (The Pile)

Max Activating Token Index: 392

Text #4

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.1511. Min Act: -0.0000

Data Index: 794480 (The Pile)

Max Activating Token Index: 561

Text #5

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.1392. Min Act: -0.0000

Data Index: 1635651 (The Pile)

Max Activating Token Index: 315

Text #6

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.1407. Min Act: -0.0000

Data Index: 6343 (The Pile)

Max Activating Token Index: 207

Text #7

Max Range: 5.4303. Min Range: -5.4303

Max Act: 4.7766. Min Act: -0.0000

Data Index: 130163 (The Pile)

Max Activating Token Index: 489

Text #8

Max Range: 5.4303. Min Range: -5.4303

Max Act: 4.9051. Min Act: -0.0000

Data Index: 1398241 (The Pile)

Max Activating Token Index: 466

Text #9

Max Range: 5.4303. Min Range: -5.4303

Max Act: 4.8820. Min Act: -0.0000

Data Index: 1823171 (The Pile)

Max Activating Token Index: 132

Text #10

Max Range: 5.4303. Min Range: -5.4303

Max Act: 4.9880. Min Act: -0.0000

Data Index: 526528 (The Pile)

Max Activating Token Index: 419

Text #11

Max Range: 5.4303. Min Range: -5.4303

Max Act: 4.5864. Min Act: -0.0000

Data Index: 1466738 (The Pile)

Max Activating Token Index: 342

Text #12

Max Range: 5.4303. Min Range: -5.4303

Max Act: 4.9384. Min Act: -0.0000

Data Index: 1392195 (The Pile)

Max Activating Token Index: 511

Text #13

Max Range: 5.4303. Min Range: -5.4303

Max Act: 4.2174. Min Act: -0.0000

Data Index: 339373 (The Pile)

Max Activating Token Index: 706

Text #14

Max Range: 5.4303. Min Range: -5.4303

Max Act: 4.7422. Min Act: -0.0000

Data Index: 1326432 (The Pile)

Max Activating Token Index: 698

Text #15

Max Range: 5.4303. Min Range: -5.4303

Max Act: 4.3520. Min Act: -0.0000

Data Index: 702780 (The Pile)

Max Activating Token Index: 565

Text #16

Max Range: 5.4303. Min Range: -5.4303

Max Act: 4.7156. Min Act: -0.0000

Data Index: 1944676 (The Pile)

Max Activating Token Index: 448

Text #17

Max Range: 5.4303. Min Range: -5.4303

Max Act: 4.6970. Min Act: -0.0000

Data Index: 1430598 (The Pile)

Max Activating Token Index: 230

Text #18

Max Range: 5.4303. Min Range: -5.4303

Max Act: 4.5122. Min Act: -0.0000

Data Index: 318304 (The Pile)

Max Activating Token Index: 548

Text #19

Max Range: 5.4303. Min Range: -5.4303

Max Act: 4.3525. Min Act: -0.0000

Data Index: 249374 (The Pile)

Max Activating Token Index: 575