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

Dataset: The Pile

Neuron 2998 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4114. Min Range: -1.4114

Max Act: 1.4114. Min Act: -0.0000

Data Index: 604037 (The Pile)

Max Activating Token Index: 156

Text #1

Max Range: 1.4114. Min Range: -1.4114

Max Act: 1.3038. Min Act: -0.0000

Data Index: 1130387 (The Pile)

Max Activating Token Index: 983

Text #2

Max Range: 1.4114. Min Range: -1.4114

Max Act: 1.2332. Min Act: -0.0000

Data Index: 815069 (The Pile)

Max Activating Token Index: 128

Text #3

Max Range: 1.4114. Min Range: -1.4114

Max Act: 1.1406. Min Act: -0.0000

Data Index: 1056144 (The Pile)

Max Activating Token Index: 310

Text #4

Max Range: 1.4114. Min Range: -1.4114

Max Act: 1.0319. Min Act: -0.0000

Data Index: 301001 (The Pile)

Max Activating Token Index: 603

Text #5

Max Range: 1.4114. Min Range: -1.4114

Max Act: 0.8201. Min Act: -0.0000

Data Index: 887740 (The Pile)

Max Activating Token Index: 568

Text #6

Max Range: 1.4114. Min Range: -1.4114

Max Act: 0.8102. Min Act: -0.0000

Data Index: 1471908 (The Pile)

Max Activating Token Index: 554

Text #7

Max Range: 1.4114. Min Range: -1.4114

Max Act: 0.7673. Min Act: -0.0000

Data Index: 679856 (The Pile)

Max Activating Token Index: 608

Text #8

Max Range: 1.4114. Min Range: -1.4114

Max Act: 0.7018. Min Act: -0.0000

Data Index: 356968 (The Pile)

Max Activating Token Index: 998

Text #9

Max Range: 1.4114. Min Range: -1.4114

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1285615 (The Pile)

Max Activating Token Index: 776

Text #10

Max Range: 1.4114. Min Range: -1.4114

Max Act: 0.7501. Min Act: -0.0000

Data Index: 864361 (The Pile)

Max Activating Token Index: 604

Text #11

Max Range: 1.4114. Min Range: -1.4114

Max Act: 0.7474. Min Act: -0.0000

Data Index: 728088 (The Pile)

Max Activating Token Index: 681

Text #12

Max Range: 1.4114. Min Range: -1.4114

Max Act: 0.7338. Min Act: -0.0000

Data Index: 626182 (The Pile)

Max Activating Token Index: 902

Text #13

Max Range: 1.4114. Min Range: -1.4114

Max Act: 0.7191. Min Act: -0.0000

Data Index: 645094 (The Pile)

Max Activating Token Index: 574

Text #14

Max Range: 1.4114. Min Range: -1.4114

Max Act: 0.6883. Min Act: -0.0000

Data Index: 895600 (The Pile)

Max Activating Token Index: 169

Text #15

Max Range: 1.4114. Min Range: -1.4114

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1274742 (The Pile)

Max Activating Token Index: 365

Text #16

Max Range: 1.4114. Min Range: -1.4114

Max Act: 0.6711. Min Act: -0.0000

Data Index: 1596976 (The Pile)

Max Activating Token Index: 716

Text #17

Max Range: 1.4114. Min Range: -1.4114

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1669933 (The Pile)

Max Activating Token Index: 408

Text #18

Max Range: 1.4114. Min Range: -1.4114

Max Act: 0.6605. Min Act: -0.0000

Data Index: 1785755 (The Pile)

Max Activating Token Index: 260

Text #19

Max Range: 1.4114. Min Range: -1.4114

Max Act: 0.6833. Min Act: -0.0000

Data Index: 1011432 (The Pile)

Max Activating Token Index: 889