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

Dataset: The Pile

Neuron 1381 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: 5.9432. Min Range: -5.9432

Max Act: 5.9432. Min Act: -0.0000

Data Index: 1156707 (The Pile)

Max Activating Token Index: 734

Text #1

Max Range: 5.9432. Min Range: -5.9432

Max Act: 5.4126. Min Act: -0.0000

Data Index: 82397 (The Pile)

Max Activating Token Index: 821

Text #2

Max Range: 5.9432. Min Range: -5.9432

Max Act: 5.5896. Min Act: -0.0000

Data Index: 1651303 (The Pile)

Max Activating Token Index: 168

Text #3

Max Range: 5.9432. Min Range: -5.9432

Max Act: 5.5580. Min Act: -0.0000

Data Index: 562463 (The Pile)

Max Activating Token Index: 262

Text #4

Max Range: 5.9432. Min Range: -5.9432

Max Act: 5.7491. Min Act: -0.0000

Data Index: 168199 (The Pile)

Max Activating Token Index: 726

Text #5

Max Range: 5.9432. Min Range: -5.9432

Max Act: 5.3703. Min Act: -0.0000

Data Index: 1176990 (The Pile)

Max Activating Token Index: 560

Text #6

Max Range: 5.9432. Min Range: -5.9432

Max Act: 5.7470. Min Act: -0.0000

Data Index: 830092 (The Pile)

Max Activating Token Index: 400

Text #7

Max Range: 5.9432. Min Range: -5.9432

Max Act: 5.3894. Min Act: -0.0000

Data Index: 1170351 (The Pile)

Max Activating Token Index: 646

Text #8

Max Range: 5.9432. Min Range: -5.9432

Max Act: 5.5292. Min Act: -0.0000

Data Index: 1174677 (The Pile)

Max Activating Token Index: 380

Text #9

Max Range: 5.9432. Min Range: -5.9432

Max Act: 5.9086. Min Act: -0.0000

Data Index: 943828 (The Pile)

Max Activating Token Index: 236

Text #10

Max Range: 5.9432. Min Range: -5.9432

Max Act: 5.7479. Min Act: -0.0000

Data Index: 1971989 (The Pile)

Max Activating Token Index: 588

Text #11

Max Range: 5.9432. Min Range: -5.9432

Max Act: 5.5506. Min Act: -0.0000

Data Index: 1718070 (The Pile)

Max Activating Token Index: 614

Text #12

Max Range: 5.9432. Min Range: -5.9432

Max Act: 5.7243. Min Act: -0.0000

Data Index: 949560 (The Pile)

Max Activating Token Index: 432

Text #13

Max Range: 5.9432. Min Range: -5.9432

Max Act: 5.4146. Min Act: -0.0000

Data Index: 560557 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 5.9432. Min Range: -5.9432

Max Act: 5.4103. Min Act: -0.0000

Data Index: 635076 (The Pile)

Max Activating Token Index: 719

Text #15

Max Range: 5.9432. Min Range: -5.9432

Max Act: 5.5615. Min Act: -0.0000

Data Index: 382210 (The Pile)

Max Activating Token Index: 549

Text #16

Max Range: 5.9432. Min Range: -5.9432

Max Act: 5.3915. Min Act: -0.0000

Data Index: 856894 (The Pile)

Max Activating Token Index: 535

Text #17

Max Range: 5.9432. Min Range: -5.9432

Max Act: 5.5637. Min Act: -0.0000

Data Index: 1867271 (The Pile)

Max Activating Token Index: 372

Text #18

Max Range: 5.9432. Min Range: -5.9432

Max Act: 5.4059. Min Act: -0.0000

Data Index: 647835 (The Pile)

Max Activating Token Index: 493

Text #19

Max Range: 5.9432. Min Range: -5.9432

Max Act: 5.2117. Min Act: -0.0000

Data Index: 1503719 (The Pile)

Max Activating Token Index: 630