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

Dataset: The Pile

Neuron 4112 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: 3.8118. Min Range: -3.8118

Max Act: 3.8118. Min Act: -0.0000

Data Index: 1845570 (The Pile)

Max Activating Token Index: 306

Text #1

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.4683. Min Act: -0.0001

Data Index: 233127 (The Pile)

Max Activating Token Index: 354

Text #2

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.5278. Min Act: -0.0000

Data Index: 1207601 (The Pile)

Max Activating Token Index: 466

Text #3

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.3531. Min Act: -0.0000

Data Index: 256547 (The Pile)

Max Activating Token Index: 497

Text #4

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.4075. Min Act: -0.0000

Data Index: 1108202 (The Pile)

Max Activating Token Index: 349

Text #5

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.5626. Min Act: -0.0000

Data Index: 1671926 (The Pile)

Max Activating Token Index: 334

Text #6

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.3411. Min Act: -0.0000

Data Index: 1736291 (The Pile)

Max Activating Token Index: 68

Text #7

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.1810. Min Act: -0.0000

Data Index: 1577465 (The Pile)

Max Activating Token Index: 462

Text #8

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.2464. Min Act: -0.0000

Data Index: 976779 (The Pile)

Max Activating Token Index: 601

Text #9

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.0604. Min Act: -0.0001

Data Index: 1140606 (The Pile)

Max Activating Token Index: 649

Text #10

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.2005. Min Act: -0.0000

Data Index: 841865 (The Pile)

Max Activating Token Index: 228

Text #11

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.1457. Min Act: -0.0000

Data Index: 905527 (The Pile)

Max Activating Token Index: 381

Text #12

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.1032. Min Act: -0.0000

Data Index: 1807445 (The Pile)

Max Activating Token Index: 362

Text #13

Max Range: 3.8118. Min Range: -3.8118

Max Act: 2.8272. Min Act: -0.0000

Data Index: 36583 (The Pile)

Max Activating Token Index: 229

Text #14

Max Range: 3.8118. Min Range: -3.8118

Max Act: 2.8319. Min Act: -0.0000

Data Index: 372890 (The Pile)

Max Activating Token Index: 500

Text #15

Max Range: 3.8118. Min Range: -3.8118

Max Act: 2.7932. Min Act: -0.0000

Data Index: 1266200 (The Pile)

Max Activating Token Index: 342

Text #16

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.0672. Min Act: -0.0000

Data Index: 1283459 (The Pile)

Max Activating Token Index: 209

Text #17

Max Range: 3.8118. Min Range: -3.8118

Max Act: 2.9396. Min Act: -0.0000

Data Index: 1039919 (The Pile)

Max Activating Token Index: 755

Text #18

Max Range: 3.8118. Min Range: -3.8118

Max Act: 2.6282. Min Act: -0.0000

Data Index: 960905 (The Pile)

Max Activating Token Index: 211

Text #19

Max Range: 3.8118. Min Range: -3.8118

Max Act: 2.8501. Min Act: -0.0000

Data Index: 781999 (The Pile)

Max Activating Token Index: 299