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

Dataset: The Pile

Neuron 1809 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.6964. Min Act: -0.0000

Data Index: 1044681 (The Pile)

Max Activating Token Index: 303

Text #1

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.5308. Min Act: -0.0000

Data Index: 1019042 (The Pile)

Max Activating Token Index: 628

Text #2

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.4569. Min Act: -0.0000

Data Index: 1793279 (The Pile)

Max Activating Token Index: 988

Text #3

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.5090. Min Act: -0.0000

Data Index: 695367 (The Pile)

Max Activating Token Index: 740

Text #4

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.3470. Min Act: -0.0000

Data Index: 415489 (The Pile)

Max Activating Token Index: 988

Text #5

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.4597. Min Act: -0.0000

Data Index: 1328188 (The Pile)

Max Activating Token Index: 631

Text #6

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.3956. Min Act: -0.0000

Data Index: 43914 (The Pile)

Max Activating Token Index: 272

Text #7

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.3369. Min Act: -0.0000

Data Index: 1919100 (The Pile)

Max Activating Token Index: 130

Text #8

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.2252. Min Act: -0.0000

Data Index: 727003 (The Pile)

Max Activating Token Index: 779

Text #9

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.3273. Min Act: -0.0000

Data Index: 1548309 (The Pile)

Max Activating Token Index: 756

Text #10

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.3602. Min Act: -0.0000

Data Index: 1435477 (The Pile)

Max Activating Token Index: 508

Text #11

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.3322. Min Act: -0.0000

Data Index: 468724 (The Pile)

Max Activating Token Index: 695

Text #12

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.2205. Min Act: -0.0000

Data Index: 416128 (The Pile)

Max Activating Token Index: 703

Text #13

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.2442. Min Act: -0.0000

Data Index: 1210770 (The Pile)

Max Activating Token Index: 624

Text #14

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.2432. Min Act: -0.0000

Data Index: 880279 (The Pile)

Max Activating Token Index: 536

Text #15

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.2396. Min Act: -0.0000

Data Index: 1762941 (The Pile)

Max Activating Token Index: 799

Text #16

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.2051. Min Act: -0.0000

Data Index: 631933 (The Pile)

Max Activating Token Index: 806

Text #17

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.3370. Min Act: -0.0000

Data Index: 368858 (The Pile)

Max Activating Token Index: 340

Text #18

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.2658. Min Act: -0.0000

Data Index: 1920890 (The Pile)

Max Activating Token Index: 956

Text #19

Max Range: 1.6964. Min Range: -1.6964

Max Act: 1.2366. Min Act: -0.0000

Data Index: 1062009 (The Pile)

Max Activating Token Index: 517