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

Dataset: The Pile

Neuron 1892 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3982. Min Act: -0.0000

Data Index: 1129223 (The Pile)

Max Activating Token Index: 503

Text #1

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3835. Min Act: -0.0000

Data Index: 477844 (The Pile)

Max Activating Token Index: 724

Text #2

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3556. Min Act: -0.0000

Data Index: 771387 (The Pile)

Max Activating Token Index: 257

Text #3

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3350. Min Act: -0.0000

Data Index: 1599741 (The Pile)

Max Activating Token Index: 335

Text #4

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3339. Min Act: -0.0001

Data Index: 980683 (The Pile)

Max Activating Token Index: 566

Text #5

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3458. Min Act: -0.0000

Data Index: 461649 (The Pile)

Max Activating Token Index: 967

Text #6

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2858. Min Act: -0.0000

Data Index: 1796225 (The Pile)

Max Activating Token Index: 988

Text #7

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3015. Min Act: -0.0000

Data Index: 413135 (The Pile)

Max Activating Token Index: 961

Text #8

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2990. Min Act: -0.0000

Data Index: 1410565 (The Pile)

Max Activating Token Index: 188

Text #9

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2950. Min Act: -0.0000

Data Index: 1900218 (The Pile)

Max Activating Token Index: 379

Text #10

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2999. Min Act: -0.0000

Data Index: 437607 (The Pile)

Max Activating Token Index: 491

Text #11

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2555. Min Act: -0.0000

Data Index: 841184 (The Pile)

Max Activating Token Index: 156

Text #12

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2405. Min Act: -0.0000

Data Index: 1953574 (The Pile)

Max Activating Token Index: 688

Text #13

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2278. Min Act: -0.0000

Data Index: 502362 (The Pile)

Max Activating Token Index: 126

Text #14

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2919. Min Act: -0.0000

Data Index: 1881052 (The Pile)

Max Activating Token Index: 958

Text #15

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1265880 (The Pile)

Max Activating Token Index: 163

Text #16

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1960856 (The Pile)

Max Activating Token Index: 573

Text #17

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2818. Min Act: -0.0000

Data Index: 1064489 (The Pile)

Max Activating Token Index: 67

Text #18

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2134. Min Act: -0.0000

Data Index: 49942 (The Pile)

Max Activating Token Index: 825

Text #19

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2601. Min Act: -0.0000

Data Index: 647885 (The Pile)

Max Activating Token Index: 157