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

Dataset: The Pile

Neuron 2989 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.4313. Min Act: -0.0000

Data Index: 843177 (The Pile)

Max Activating Token Index: 223

Text #1

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1331083 (The Pile)

Max Activating Token Index: 93

Text #2

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.4093. Min Act: -0.0000

Data Index: 254966 (The Pile)

Max Activating Token Index: 64

Text #3

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3938. Min Act: -0.0000

Data Index: 1701653 (The Pile)

Max Activating Token Index: 396

Text #4

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3696. Min Act: -0.0000

Data Index: 1230503 (The Pile)

Max Activating Token Index: 471

Text #5

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3448. Min Act: -0.0000

Data Index: 567012 (The Pile)

Max Activating Token Index: 658

Text #6

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3506. Min Act: -0.0000

Data Index: 1216817 (The Pile)

Max Activating Token Index: 963

Text #7

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3438. Min Act: -0.0000

Data Index: 85753 (The Pile)

Max Activating Token Index: 750

Text #8

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3545. Min Act: -0.0000

Data Index: 1082637 (The Pile)

Max Activating Token Index: 778

Text #9

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3375. Min Act: -0.0000

Data Index: 310183 (The Pile)

Max Activating Token Index: 492

Text #10

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3101. Min Act: -0.0000

Data Index: 42650 (The Pile)

Max Activating Token Index: 272

Text #11

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3316. Min Act: -0.0000

Data Index: 1570087 (The Pile)

Max Activating Token Index: 336

Text #12

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3274. Min Act: -0.0000

Data Index: 1205239 (The Pile)

Max Activating Token Index: 398

Text #13

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3156. Min Act: -0.0000

Data Index: 1845551 (The Pile)

Max Activating Token Index: 310

Text #14

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3211. Min Act: -0.0000

Data Index: 43706 (The Pile)

Max Activating Token Index: 363

Text #15

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3104. Min Act: -0.0000

Data Index: 700886 (The Pile)

Max Activating Token Index: 552

Text #16

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1106906 (The Pile)

Max Activating Token Index: 48

Text #17

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1446128 (The Pile)

Max Activating Token Index: 682

Text #18

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2990. Min Act: -0.0000

Data Index: 818824 (The Pile)

Max Activating Token Index: 209

Text #19

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3111. Min Act: -0.0000

Data Index: 1594285 (The Pile)

Max Activating Token Index: 81