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

Dataset: The Pile

Neuron 1109 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0129. Min Range: -2.0129

Max Act: 2.0129. Min Act: -0.0000

Data Index: 1513831 (The Pile)

Max Activating Token Index: 137

Text #1

Max Range: 2.0129. Min Range: -2.0129

Max Act: 1.8200. Min Act: -0.0000

Data Index: 546342 (The Pile)

Max Activating Token Index: 83

Text #2

Max Range: 2.0129. Min Range: -2.0129

Max Act: 1.6767. Min Act: -0.0000

Data Index: 1365557 (The Pile)

Max Activating Token Index: 894

Text #3

Max Range: 2.0129. Min Range: -2.0129

Max Act: 1.6017. Min Act: -0.0000

Data Index: 1529625 (The Pile)

Max Activating Token Index: 762

Text #4

Max Range: 2.0129. Min Range: -2.0129

Max Act: 1.6788. Min Act: -0.0000

Data Index: 1298843 (The Pile)

Max Activating Token Index: 177

Text #5

Max Range: 2.0129. Min Range: -2.0129

Max Act: 1.4347. Min Act: -0.0000

Data Index: 760405 (The Pile)

Max Activating Token Index: 801

Text #6

Max Range: 2.0129. Min Range: -2.0129

Max Act: 1.5921. Min Act: -0.0000

Data Index: 1164082 (The Pile)

Max Activating Token Index: 686

Text #7

Max Range: 2.0129. Min Range: -2.0129

Max Act: 1.4057. Min Act: -0.0000

Data Index: 1565245 (The Pile)

Max Activating Token Index: 56

Text #8

Max Range: 2.0129. Min Range: -2.0129

Max Act: 1.5171. Min Act: -0.0000

Data Index: 893225 (The Pile)

Max Activating Token Index: 297

Text #9

Max Range: 2.0129. Min Range: -2.0129

Max Act: 1.4111. Min Act: -0.0000

Data Index: 1637859 (The Pile)

Max Activating Token Index: 78

Text #10

Max Range: 2.0129. Min Range: -2.0129

Max Act: 1.4872. Min Act: -0.0000

Data Index: 612607 (The Pile)

Max Activating Token Index: 488

Text #11

Max Range: 2.0129. Min Range: -2.0129

Max Act: 1.2938. Min Act: -0.0000

Data Index: 387569 (The Pile)

Max Activating Token Index: 733

Text #12

Max Range: 2.0129. Min Range: -2.0129

Max Act: 1.3469. Min Act: -0.0000

Data Index: 442678 (The Pile)

Max Activating Token Index: 81

Text #13

Max Range: 2.0129. Min Range: -2.0129

Max Act: 1.4190. Min Act: -0.0000

Data Index: 680730 (The Pile)

Max Activating Token Index: 54

Text #14

Max Range: 2.0129. Min Range: -2.0129

Max Act: 1.3425. Min Act: -0.0000

Data Index: 1635338 (The Pile)

Max Activating Token Index: 922

Text #15

Max Range: 2.0129. Min Range: -2.0129

Max Act: 1.3424. Min Act: -0.0000

Data Index: 1882290 (The Pile)

Max Activating Token Index: 50

Text #16

Max Range: 2.0129. Min Range: -2.0129

Max Act: 1.3225. Min Act: -0.0000

Data Index: 521408 (The Pile)

Max Activating Token Index: 127

Text #17

Max Range: 2.0129. Min Range: -2.0129

Max Act: 1.2420. Min Act: -0.0000

Data Index: 796140 (The Pile)

Max Activating Token Index: 380

Text #18

Max Range: 2.0129. Min Range: -2.0129

Max Act: 1.2315. Min Act: -0.0000

Data Index: 926563 (The Pile)

Max Activating Token Index: 457

Text #19

Max Range: 2.0129. Min Range: -2.0129

Max Act: 1.2148. Min Act: -0.0000

Data Index: 1166043 (The Pile)

Max Activating Token Index: 748