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

Dataset: The Pile

Neuron 2967 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: 7.6989. Min Range: -7.6989

Max Act: 7.4597. Min Act: -0.0000

Data Index: 1809288 (The Pile)

Max Activating Token Index: 974

Text #1

Max Range: 7.6989. Min Range: -7.6989

Max Act: 7.6989. Min Act: -0.0000

Data Index: 421889 (The Pile)

Max Activating Token Index: 610

Text #2

Max Range: 7.6989. Min Range: -7.6989

Max Act: 6.7817. Min Act: -0.0000

Data Index: 1226007 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 7.6989. Min Range: -7.6989

Max Act: 7.0489. Min Act: -0.0000

Data Index: 353945 (The Pile)

Max Activating Token Index: 205

Text #4

Max Range: 7.6989. Min Range: -7.6989

Max Act: 6.6975. Min Act: -0.0000

Data Index: 635969 (The Pile)

Max Activating Token Index: 194

Text #5

Max Range: 7.6989. Min Range: -7.6989

Max Act: 6.8800. Min Act: -0.0000

Data Index: 646920 (The Pile)

Max Activating Token Index: 31

Text #6

Max Range: 7.6989. Min Range: -7.6989

Max Act: 7.0572. Min Act: -0.0000

Data Index: 1170650 (The Pile)

Max Activating Token Index: 858

Text #7

Max Range: 7.6989. Min Range: -7.6989

Max Act: 7.0168. Min Act: -0.0000

Data Index: 262449 (The Pile)

Max Activating Token Index: 51

Text #8

Max Range: 7.6989. Min Range: -7.6989

Max Act: 6.7179. Min Act: -0.0000

Data Index: 1911841 (The Pile)

Max Activating Token Index: 633

Text #9

Max Range: 7.6989. Min Range: -7.6989

Max Act: 6.6494. Min Act: -0.0000

Data Index: 1727656 (The Pile)

Max Activating Token Index: 579

Text #10

Max Range: 7.6989. Min Range: -7.6989

Max Act: 6.6319. Min Act: -0.0000

Data Index: 1053534 (The Pile)

Max Activating Token Index: 45

Text #11

Max Range: 7.6989. Min Range: -7.6989

Max Act: 6.3859. Min Act: -0.0000

Data Index: 1197512 (The Pile)

Max Activating Token Index: 658

Text #12

Max Range: 7.6989. Min Range: -7.6989

Max Act: 6.2944. Min Act: -0.0000

Data Index: 606757 (The Pile)

Max Activating Token Index: 513

Text #13

Max Range: 7.6989. Min Range: -7.6989

Max Act: 6.4645. Min Act: -0.0000

Data Index: 1857261 (The Pile)

Max Activating Token Index: 581

Text #14

Max Range: 7.6989. Min Range: -7.6989

Max Act: 6.2792. Min Act: -0.0000

Data Index: 1466826 (The Pile)

Max Activating Token Index: 211

Text #15

Max Range: 7.6989. Min Range: -7.6989

Max Act: 6.2706. Min Act: -0.0000

Data Index: 1712505 (The Pile)

Max Activating Token Index: 259

Text #16

Max Range: 7.6989. Min Range: -7.6989

Max Act: 6.2080. Min Act: -0.0000

Data Index: 518782 (The Pile)

Max Activating Token Index: 573

Text #17

Max Range: 7.6989. Min Range: -7.6989

Max Act: 6.1479. Min Act: -0.0000

Data Index: 1703800 (The Pile)

Max Activating Token Index: 801

Text #18

Max Range: 7.6989. Min Range: -7.6989

Max Act: 6.0814. Min Act: -0.0000

Data Index: 1977064 (The Pile)

Max Activating Token Index: 507

Text #19

Max Range: 7.6989. Min Range: -7.6989

Max Act: 6.0474. Min Act: -0.0000

Data Index: 1912848 (The Pile)

Max Activating Token Index: 918