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

Dataset: The Pile

Neuron 3082 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: 1.4458. Min Range: -1.4458

Max Act: 1.4458. Min Act: -0.0000

Data Index: 875892 (The Pile)

Max Activating Token Index: 614

Text #1

Max Range: 1.4458. Min Range: -1.4458

Max Act: 1.2178. Min Act: -0.0000

Data Index: 699841 (The Pile)

Max Activating Token Index: 382

Text #2

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9988. Min Act: -0.0000

Data Index: 1199609 (The Pile)

Max Activating Token Index: 606

Text #3

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9137. Min Act: -0.0000

Data Index: 676764 (The Pile)

Max Activating Token Index: 107

Text #4

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9731. Min Act: -0.0000

Data Index: 1158867 (The Pile)

Max Activating Token Index: 837

Text #5

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1090662 (The Pile)

Max Activating Token Index: 611

Text #6

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9959. Min Act: -0.0000

Data Index: 259483 (The Pile)

Max Activating Token Index: 241

Text #7

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9238. Min Act: -0.0000

Data Index: 1042702 (The Pile)

Max Activating Token Index: 702

Text #8

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.8982. Min Act: -0.0000

Data Index: 606059 (The Pile)

Max Activating Token Index: 80

Text #9

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.8773. Min Act: -0.0000

Data Index: 501745 (The Pile)

Max Activating Token Index: 147

Text #10

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1360484 (The Pile)

Max Activating Token Index: 469

Text #11

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.8723. Min Act: -0.0000

Data Index: 809230 (The Pile)

Max Activating Token Index: 251

Text #12

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9118. Min Act: -0.0000

Data Index: 1892553 (The Pile)

Max Activating Token Index: 208

Text #13

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.8967. Min Act: -0.0000

Data Index: 1193281 (The Pile)

Max Activating Token Index: 54

Text #14

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.8061. Min Act: -0.0000

Data Index: 1740884 (The Pile)

Max Activating Token Index: 849

Text #15

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9345. Min Act: -0.0000

Data Index: 791027 (The Pile)

Max Activating Token Index: 69

Text #16

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1584026 (The Pile)

Max Activating Token Index: 575

Text #17

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1929757 (The Pile)

Max Activating Token Index: 855

Text #18

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.7699. Min Act: -0.0000

Data Index: 1585111 (The Pile)

Max Activating Token Index: 87

Text #19

Max Range: 1.4458. Min Range: -1.4458

Max Act: 0.8636. Min Act: -0.0000

Data Index: 1364098 (The Pile)

Max Activating Token Index: 484