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

Dataset: The Pile

Neuron 1396 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4640. Min Range: -1.4640

Max Act: 1.4640. Min Act: -0.0000

Data Index: 1678254 (The Pile)

Max Activating Token Index: 760

Text #1

Max Range: 1.4640. Min Range: -1.4640

Max Act: 0.9864. Min Act: -0.0000

Data Index: 1242641 (The Pile)

Max Activating Token Index: 970

Text #2

Max Range: 1.4640. Min Range: -1.4640

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1853000 (The Pile)

Max Activating Token Index: 113

Text #3

Max Range: 1.4640. Min Range: -1.4640

Max Act: 0.9173. Min Act: -0.0000

Data Index: 784775 (The Pile)

Max Activating Token Index: 547

Text #4

Max Range: 1.4640. Min Range: -1.4640

Max Act: 0.7260. Min Act: -0.0000

Data Index: 1599810 (The Pile)

Max Activating Token Index: 74

Text #5

Max Range: 1.4640. Min Range: -1.4640

Max Act: 0.7567. Min Act: -0.0000

Data Index: 1161074 (The Pile)

Max Activating Token Index: 856

Text #6

Max Range: 1.4640. Min Range: -1.4640

Max Act: 0.7251. Min Act: -0.0000

Data Index: 1076704 (The Pile)

Max Activating Token Index: 814

Text #7

Max Range: 1.4640. Min Range: -1.4640

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1994322 (The Pile)

Max Activating Token Index: 325

Text #8

Max Range: 1.4640. Min Range: -1.4640

Max Act: 0.6867. Min Act: -0.0000

Data Index: 581224 (The Pile)

Max Activating Token Index: 768

Text #9

Max Range: 1.4640. Min Range: -1.4640

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1472400 (The Pile)

Max Activating Token Index: 258

Text #10

Max Range: 1.4640. Min Range: -1.4640

Max Act: 0.7048. Min Act: -0.0000

Data Index: 76826 (The Pile)

Max Activating Token Index: 768

Text #11

Max Range: 1.4640. Min Range: -1.4640

Max Act: 0.7206. Min Act: -0.0000

Data Index: 571017 (The Pile)

Max Activating Token Index: 61

Text #12

Max Range: 1.4640. Min Range: -1.4640

Max Act: 0.7098. Min Act: -0.0000

Data Index: 1815458 (The Pile)

Max Activating Token Index: 361

Text #13

Max Range: 1.4640. Min Range: -1.4640

Max Act: 0.6562. Min Act: -0.0000

Data Index: 181215 (The Pile)

Max Activating Token Index: 254

Text #14

Max Range: 1.4640. Min Range: -1.4640

Max Act: 0.6770. Min Act: 0.0000

Data Index: 1686674 (The Pile)

Max Activating Token Index: 307

Text #15

Max Range: 1.4640. Min Range: -1.4640

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1159545 (The Pile)

Max Activating Token Index: 806

Text #16

Max Range: 1.4640. Min Range: -1.4640

Max Act: 0.7016. Min Act: -0.0000

Data Index: 931520 (The Pile)

Max Activating Token Index: 28

Text #17

Max Range: 1.4640. Min Range: -1.4640

Max Act: 0.6291. Min Act: -0.0000

Data Index: 1746744 (The Pile)

Max Activating Token Index: 206

Text #18

Max Range: 1.4640. Min Range: -1.4640

Max Act: 0.6470. Min Act: -0.0000

Data Index: 76152 (The Pile)

Max Activating Token Index: 815

Text #19

Max Range: 1.4640. Min Range: -1.4640

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1367331 (The Pile)

Max Activating Token Index: 180