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

Dataset: The Pile

Neuron 14 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: 1.2832. Min Range: -1.2832

Max Act: 1.2832. Min Act: 0.0000

Data Index: 919335 (The Pile)

Max Activating Token Index: 171

Text #1

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.1535. Min Act: -0.0000

Data Index: 741075 (The Pile)

Max Activating Token Index: 209

Text #2

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.2639. Min Act: -0.0000

Data Index: 263562 (The Pile)

Max Activating Token Index: 774

Text #3

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.1964. Min Act: -0.0000

Data Index: 1784936 (The Pile)

Max Activating Token Index: 140

Text #4

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.1605. Min Act: 0.0000

Data Index: 1799254 (The Pile)

Max Activating Token Index: 286

Text #5

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.1248. Min Act: -0.0000

Data Index: 1131870 (The Pile)

Max Activating Token Index: 544

Text #6

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.0934. Min Act: -0.0000

Data Index: 1819 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.0365. Min Act: -0.0000

Data Index: 367748 (The Pile)

Max Activating Token Index: 552

Text #8

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.1166. Min Act: -0.0000

Data Index: 1163620 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.1270. Min Act: -0.0000

Data Index: 1713832 (The Pile)

Max Activating Token Index: 815

Text #10

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.0375. Min Act: -0.0000

Data Index: 66517 (The Pile)

Max Activating Token Index: 510

Text #11

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.0696. Min Act: -0.0000

Data Index: 1862097 (The Pile)

Max Activating Token Index: 486

Text #12

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.9733. Min Act: -0.0000

Data Index: 692251 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.1115. Min Act: -0.0000

Data Index: 553741 (The Pile)

Max Activating Token Index: 626

Text #14

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.0423. Min Act: 0.0000

Data Index: 874002 (The Pile)

Max Activating Token Index: 276

Text #15

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.0177. Min Act: -0.0000

Data Index: 246157 (The Pile)

Max Activating Token Index: 392

Text #16

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.0016. Min Act: -0.0000

Data Index: 1235271 (The Pile)

Max Activating Token Index: 190

Text #17

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.9679. Min Act: -0.0000

Data Index: 106502 (The Pile)

Max Activating Token Index: 528

Text #18

Max Range: 1.2832. Min Range: -1.2832

Max Act: 0.9178. Min Act: -0.0000

Data Index: 1855165 (The Pile)

Max Activating Token Index: 348

Text #19

Max Range: 1.2832. Min Range: -1.2832

Max Act: 1.0233. Min Act: -0.0000

Data Index: 1093667 (The Pile)

Max Activating Token Index: 526