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

Dataset: The Pile

Neuron 2003 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: 1.0288. Min Range: -1.0288

Max Act: 0.9975. Min Act: -0.0000

Data Index: 981541 (The Pile)

Max Activating Token Index: 937

Text #1

Max Range: 1.0288. Min Range: -1.0288

Max Act: 1.0288. Min Act: -0.0000

Data Index: 1634365 (The Pile)

Max Activating Token Index: 565

Text #2

Max Range: 1.0288. Min Range: -1.0288

Max Act: 1.0014. Min Act: -0.0000

Data Index: 1305727 (The Pile)

Max Activating Token Index: 272

Text #3

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.9905. Min Act: -0.0000

Data Index: 1882419 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 1.0288. Min Range: -1.0288

Max Act: 1.0166. Min Act: -0.0000

Data Index: 845547 (The Pile)

Max Activating Token Index: 818

Text #5

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.9478. Min Act: -0.0000

Data Index: 734403 (The Pile)

Max Activating Token Index: 54

Text #6

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.9547. Min Act: -0.0000

Data Index: 1017332 (The Pile)

Max Activating Token Index: 473

Text #7

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.9183. Min Act: -0.0000

Data Index: 807072 (The Pile)

Max Activating Token Index: 875

Text #8

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.9538. Min Act: -0.0000

Data Index: 373574 (The Pile)

Max Activating Token Index: 619

Text #9

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.9015. Min Act: -0.0000

Data Index: 599557 (The Pile)

Max Activating Token Index: 573

Text #10

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1859833 (The Pile)

Max Activating Token Index: 232

Text #11

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8577. Min Act: -0.0000

Data Index: 1483830 (The Pile)

Max Activating Token Index: 368

Text #12

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8284. Min Act: -0.0000

Data Index: 684275 (The Pile)

Max Activating Token Index: 912

Text #13

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1511319 (The Pile)

Max Activating Token Index: 57

Text #14

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8285. Min Act: -0.0000

Data Index: 1068699 (The Pile)

Max Activating Token Index: 268

Text #15

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8185. Min Act: -0.0000

Data Index: 1973235 (The Pile)

Max Activating Token Index: 355

Text #16

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.7689. Min Act: -0.0000

Data Index: 7765 (The Pile)

Max Activating Token Index: 673

Text #17

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8078. Min Act: -0.0000

Data Index: 935219 (The Pile)

Max Activating Token Index: 834

Text #18

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.7507. Min Act: -0.0000

Data Index: 1183718 (The Pile)

Max Activating Token Index: 61

Text #19

Max Range: 1.0288. Min Range: -1.0288

Max Act: 0.8177. Min Act: -0.0000

Data Index: 501380 (The Pile)

Max Activating Token Index: 915