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

Dataset: The Pile

Neuron 628 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: 1.5452. Min Range: -1.5452

Max Act: 1.5452. Min Act: -0.0000

Data Index: 655374 (The Pile)

Max Activating Token Index: 231

Text #1

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.4257. Min Act: -0.0000

Data Index: 1649995 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.2080. Min Act: -0.0000

Data Index: 270761 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.1339. Min Act: -0.0000

Data Index: 168345 (The Pile)

Max Activating Token Index: 23

Text #4

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.0548. Min Act: -0.0000

Data Index: 1184394 (The Pile)

Max Activating Token Index: 137

Text #5

Max Range: 1.5452. Min Range: -1.5452

Max Act: 0.9857. Min Act: -0.0000

Data Index: 1891592 (The Pile)

Max Activating Token Index: 388

Text #6

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.0274. Min Act: -0.0000

Data Index: 1989950 (The Pile)

Max Activating Token Index: 744

Text #7

Max Range: 1.5452. Min Range: -1.5452

Max Act: 0.9279. Min Act: -0.0000

Data Index: 618440 (The Pile)

Max Activating Token Index: 135

Text #8

Max Range: 1.5452. Min Range: -1.5452

Max Act: 0.9239. Min Act: -0.0000

Data Index: 112904 (The Pile)

Max Activating Token Index: 445

Text #9

Max Range: 1.5452. Min Range: -1.5452

Max Act: 0.9134. Min Act: -0.0000

Data Index: 806835 (The Pile)

Max Activating Token Index: 763

Text #10

Max Range: 1.5452. Min Range: -1.5452

Max Act: 0.8701. Min Act: -0.0000

Data Index: 1386024 (The Pile)

Max Activating Token Index: 246

Text #11

Max Range: 1.5452. Min Range: -1.5452

Max Act: 0.9578. Min Act: -0.0000

Data Index: 998012 (The Pile)

Max Activating Token Index: 246

Text #12

Max Range: 1.5452. Min Range: -1.5452

Max Act: 0.8112. Min Act: -0.0000

Data Index: 746316 (The Pile)

Max Activating Token Index: 521

Text #13

Max Range: 1.5452. Min Range: -1.5452

Max Act: 0.9683. Min Act: -0.0000

Data Index: 506403 (The Pile)

Max Activating Token Index: 57

Text #14

Max Range: 1.5452. Min Range: -1.5452

Max Act: 0.7510. Min Act: -0.0000

Data Index: 1709882 (The Pile)

Max Activating Token Index: 921

Text #15

Max Range: 1.5452. Min Range: -1.5452

Max Act: 0.7385. Min Act: -0.0000

Data Index: 1029261 (The Pile)

Max Activating Token Index: 644

Text #16

Max Range: 1.5452. Min Range: -1.5452

Max Act: 0.7790. Min Act: 0.0000

Data Index: 1463460 (The Pile)

Max Activating Token Index: 801

Text #17

Max Range: 1.5452. Min Range: -1.5452

Max Act: 0.8131. Min Act: -0.0000

Data Index: 93674 (The Pile)

Max Activating Token Index: 290

Text #18

Max Range: 1.5452. Min Range: -1.5452

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1458467 (The Pile)

Max Activating Token Index: 813

Text #19

Max Range: 1.5452. Min Range: -1.5452

Max Act: 0.7437. Min Act: -0.0000

Data Index: 1344102 (The Pile)

Max Activating Token Index: 106