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

Dataset: The Pile

Neuron 3097 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8414. Min Range: -1.8414

Max Act: 1.8414. Min Act: -0.0000

Data Index: 678283 (The Pile)

Max Activating Token Index: 231

Text #1

Max Range: 1.8414. Min Range: -1.8414

Max Act: 1.1944. Min Act: -0.0000

Data Index: 1012749 (The Pile)

Max Activating Token Index: 724

Text #2

Max Range: 1.8414. Min Range: -1.8414

Max Act: 1.2060. Min Act: -0.0000

Data Index: 377939 (The Pile)

Max Activating Token Index: 783

Text #3

Max Range: 1.8414. Min Range: -1.8414

Max Act: 1.1302. Min Act: -0.0000

Data Index: 786115 (The Pile)

Max Activating Token Index: 763

Text #4

Max Range: 1.8414. Min Range: -1.8414

Max Act: 1.0996. Min Act: 0.0000

Data Index: 1857029 (The Pile)

Max Activating Token Index: 421

Text #5

Max Range: 1.8414. Min Range: -1.8414

Max Act: 1.0936. Min Act: -0.0000

Data Index: 773221 (The Pile)

Max Activating Token Index: 523

Text #6

Max Range: 1.8414. Min Range: -1.8414

Max Act: 1.0715. Min Act: -0.0000

Data Index: 482070 (The Pile)

Max Activating Token Index: 114

Text #7

Max Range: 1.8414. Min Range: -1.8414

Max Act: 1.0278. Min Act: -0.0000

Data Index: 1046283 (The Pile)

Max Activating Token Index: 912

Text #8

Max Range: 1.8414. Min Range: -1.8414

Max Act: 1.0361. Min Act: -0.0000

Data Index: 1454000 (The Pile)

Max Activating Token Index: 479

Text #9

Max Range: 1.8414. Min Range: -1.8414

Max Act: 0.9525. Min Act: -0.0000

Data Index: 854510 (The Pile)

Max Activating Token Index: 1010

Text #10

Max Range: 1.8414. Min Range: -1.8414

Max Act: 0.9673. Min Act: -0.0000

Data Index: 1908869 (The Pile)

Max Activating Token Index: 910

Text #11

Max Range: 1.8414. Min Range: -1.8414

Max Act: 0.9638. Min Act: -0.0000

Data Index: 902427 (The Pile)

Max Activating Token Index: 920

Text #12

Max Range: 1.8414. Min Range: -1.8414

Max Act: 1.0253. Min Act: 0.0000

Data Index: 1832306 (The Pile)

Max Activating Token Index: 491

Text #13

Max Range: 1.8414. Min Range: -1.8414

Max Act: 0.9669. Min Act: 0.0000

Data Index: 508438 (The Pile)

Max Activating Token Index: 1009

Text #14

Max Range: 1.8414. Min Range: -1.8414

Max Act: 0.9577. Min Act: -0.0000

Data Index: 1334993 (The Pile)

Max Activating Token Index: 151

Text #15

Max Range: 1.8414. Min Range: -1.8414

Max Act: 1.0179. Min Act: -0.0000

Data Index: 1822170 (The Pile)

Max Activating Token Index: 528

Text #16

Max Range: 1.8414. Min Range: -1.8414

Max Act: 0.9997. Min Act: -0.0000

Data Index: 272104 (The Pile)

Max Activating Token Index: 231

Text #17

Max Range: 1.8414. Min Range: -1.8414

Max Act: 0.9070. Min Act: -0.0000

Data Index: 263110 (The Pile)

Max Activating Token Index: 576

Text #18

Max Range: 1.8414. Min Range: -1.8414

Max Act: 0.9855. Min Act: -0.0000

Data Index: 1976024 (The Pile)

Max Activating Token Index: 480

Text #19

Max Range: 1.8414. Min Range: -1.8414

Max Act: 0.9199. Min Act: -0.0000

Data Index: 1478001 (The Pile)

Max Activating Token Index: 34