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

Dataset: The Pile

Neuron 2158 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: 0.7543. Min Range: -0.7543

Max Act: 0.7009. Min Act: -0.0000

Data Index: 1124706 (The Pile)

Max Activating Token Index: 619

Text #1

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6680. Min Act: -0.0000

Data Index: 1926194 (The Pile)

Max Activating Token Index: 476

Text #2

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.7543. Min Act: -0.0000

Data Index: 79832 (The Pile)

Max Activating Token Index: 52

Text #3

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6283. Min Act: -0.0000

Data Index: 574478 (The Pile)

Max Activating Token Index: 570

Text #4

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1254094 (The Pile)

Max Activating Token Index: 615

Text #5

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1374314 (The Pile)

Max Activating Token Index: 518

Text #6

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.7496. Min Act: -0.0000

Data Index: 1593067 (The Pile)

Max Activating Token Index: 977

Text #7

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1243662 (The Pile)

Max Activating Token Index: 1004

Text #8

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1936123 (The Pile)

Max Activating Token Index: 385

Text #9

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1442900 (The Pile)

Max Activating Token Index: 87

Text #10

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1906036 (The Pile)

Max Activating Token Index: 784

Text #11

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1456310 (The Pile)

Max Activating Token Index: 34

Text #12

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6309. Min Act: -0.0000

Data Index: 1323439 (The Pile)

Max Activating Token Index: 78

Text #13

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6290. Min Act: -0.0000

Data Index: 1073833 (The Pile)

Max Activating Token Index: 534

Text #14

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6200. Min Act: -0.0000

Data Index: 813194 (The Pile)

Max Activating Token Index: 243

Text #15

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1594129 (The Pile)

Max Activating Token Index: 602

Text #16

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6001. Min Act: 0.0000

Data Index: 357177 (The Pile)

Max Activating Token Index: 76

Text #17

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.5929. Min Act: -0.0000

Data Index: 923406 (The Pile)

Max Activating Token Index: 980

Text #18

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1192037 (The Pile)

Max Activating Token Index: 775

Text #19

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.5487. Min Act: -0.0000

Data Index: 399158 (The Pile)

Max Activating Token Index: 465