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

Dataset: The Pile

Neuron 62 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1743205 (The Pile)

Max Activating Token Index: 124

Text #1

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5043. Min Act: -0.0000

Data Index: 421810 (The Pile)

Max Activating Token Index: 19

Text #2

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4940. Min Act: -0.0000

Data Index: 1139343 (The Pile)

Max Activating Token Index: 646

Text #3

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1652643 (The Pile)

Max Activating Token Index: 905

Text #4

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4598. Min Act: -0.0000

Data Index: 1343472 (The Pile)

Max Activating Token Index: 597

Text #5

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4456. Min Act: -0.0000

Data Index: 89940 (The Pile)

Max Activating Token Index: 81

Text #6

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4471. Min Act: -0.0000

Data Index: 1603300 (The Pile)

Max Activating Token Index: 573

Text #7

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4272. Min Act: -0.0000

Data Index: 947817 (The Pile)

Max Activating Token Index: 38

Text #8

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4320. Min Act: -0.0000

Data Index: 973853 (The Pile)

Max Activating Token Index: 712

Text #9

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.3942. Min Act: -0.0000

Data Index: 630250 (The Pile)

Max Activating Token Index: 663

Text #10

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4525. Min Act: -0.0000

Data Index: 1143119 (The Pile)

Max Activating Token Index: 45

Text #11

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4093. Min Act: -0.0000

Data Index: 801731 (The Pile)

Max Activating Token Index: 336

Text #12

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4076. Min Act: -0.0000

Data Index: 477356 (The Pile)

Max Activating Token Index: 838

Text #13

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.3644. Min Act: -0.0000

Data Index: 649224 (The Pile)

Max Activating Token Index: 573

Text #14

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1436877 (The Pile)

Max Activating Token Index: 978

Text #15

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.3942. Min Act: -0.0000

Data Index: 1236628 (The Pile)

Max Activating Token Index: 479

Text #16

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.3814. Min Act: -0.0000

Data Index: 1733832 (The Pile)

Max Activating Token Index: 34

Text #17

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1398849 (The Pile)

Max Activating Token Index: 936

Text #18

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.3696. Min Act: -0.0000

Data Index: 1245951 (The Pile)

Max Activating Token Index: 802

Text #19

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.3748. Min Act: -0.0000

Data Index: 172144 (The Pile)

Max Activating Token Index: 163