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

Dataset: The Pile

Neuron 4028 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: 1.7802. Min Range: -1.7802

Max Act: 1.6930. Min Act: -0.0000

Data Index: 384187 (The Pile)

Max Activating Token Index: 719

Text #1

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.7802. Min Act: -0.0000

Data Index: 365413 (The Pile)

Max Activating Token Index: 494

Text #2

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.7588. Min Act: -0.0000

Data Index: 906596 (The Pile)

Max Activating Token Index: 373

Text #3

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.7005. Min Act: -0.0000

Data Index: 837713 (The Pile)

Max Activating Token Index: 98

Text #4

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.5432. Min Act: -0.0000

Data Index: 122034 (The Pile)

Max Activating Token Index: 559

Text #5

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.6333. Min Act: -0.0000

Data Index: 1367034 (The Pile)

Max Activating Token Index: 429

Text #6

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.6262. Min Act: -0.0000

Data Index: 826321 (The Pile)

Max Activating Token Index: 139

Text #7

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.6958. Min Act: -0.0000

Data Index: 1605 (The Pile)

Max Activating Token Index: 764

Text #8

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.5862. Min Act: -0.0000

Data Index: 1639293 (The Pile)

Max Activating Token Index: 728

Text #9

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.3346. Min Act: -0.0000

Data Index: 185050 (The Pile)

Max Activating Token Index: 742

Text #10

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.5626. Min Act: -0.0000

Data Index: 230943 (The Pile)

Max Activating Token Index: 909

Text #11

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.5347. Min Act: -0.0000

Data Index: 1449912 (The Pile)

Max Activating Token Index: 186

Text #12

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.6123. Min Act: -0.0000

Data Index: 910912 (The Pile)

Max Activating Token Index: 472

Text #13

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.5123. Min Act: -0.0000

Data Index: 781997 (The Pile)

Max Activating Token Index: 267

Text #14

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.5128. Min Act: -0.0000

Data Index: 264457 (The Pile)

Max Activating Token Index: 977

Text #15

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.4230. Min Act: -0.0000

Data Index: 1130253 (The Pile)

Max Activating Token Index: 152

Text #16

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.4964. Min Act: -0.0000

Data Index: 1580837 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.4793. Min Act: -0.0000

Data Index: 559532 (The Pile)

Max Activating Token Index: 467

Text #18

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.3642. Min Act: -0.0000

Data Index: 1389979 (The Pile)

Max Activating Token Index: 957

Text #19

Max Range: 1.7802. Min Range: -1.7802

Max Act: 1.4485. Min Act: -0.0000

Data Index: 377817 (The Pile)

Max Activating Token Index: 310