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

Dataset: The Pile

Neuron 5027 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: 1.0920. Min Range: -1.0920

Max Act: 1.0920. Min Act: -0.0000

Data Index: 1583171 (The Pile)

Max Activating Token Index: 82

Text #1

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.9045. Min Act: -0.0000

Data Index: 555710 (The Pile)

Max Activating Token Index: 115

Text #2

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.8588. Min Act: -0.0000

Data Index: 1074960 (The Pile)

Max Activating Token Index: 70

Text #3

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.9302. Min Act: -0.0000

Data Index: 1743387 (The Pile)

Max Activating Token Index: 281

Text #4

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.8095. Min Act: -0.0000

Data Index: 1379306 (The Pile)

Max Activating Token Index: 815

Text #5

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.8307. Min Act: -0.0000

Data Index: 1967732 (The Pile)

Max Activating Token Index: 61

Text #6

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.8388. Min Act: -0.0000

Data Index: 1909137 (The Pile)

Max Activating Token Index: 639

Text #7

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.7802. Min Act: -0.0000

Data Index: 415810 (The Pile)

Max Activating Token Index: 779

Text #8

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.7608. Min Act: -0.0000

Data Index: 300852 (The Pile)

Max Activating Token Index: 879

Text #9

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.8026. Min Act: -0.0000

Data Index: 486483 (The Pile)

Max Activating Token Index: 99

Text #10

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.7458. Min Act: -0.0000

Data Index: 385122 (The Pile)

Max Activating Token Index: 341

Text #11

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.7649. Min Act: -0.0000

Data Index: 389676 (The Pile)

Max Activating Token Index: 59

Text #12

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.6423. Min Act: -0.0000

Data Index: 1267174 (The Pile)

Max Activating Token Index: 100

Text #13

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.7325. Min Act: -0.0000

Data Index: 630665 (The Pile)

Max Activating Token Index: 257

Text #14

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.7038. Min Act: -0.0000

Data Index: 201795 (The Pile)

Max Activating Token Index: 1004

Text #15

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.7179. Min Act: -0.0000

Data Index: 1848586 (The Pile)

Max Activating Token Index: 82

Text #16

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.6825. Min Act: -0.0000

Data Index: 200758 (The Pile)

Max Activating Token Index: 397

Text #17

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.6502. Min Act: -0.0000

Data Index: 1689034 (The Pile)

Max Activating Token Index: 637

Text #18

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1795909 (The Pile)

Max Activating Token Index: 151

Text #19

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.6740. Min Act: -0.0000

Data Index: 352435 (The Pile)

Max Activating Token Index: 894