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

Dataset: The Pile

Neuron 4135 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3937. Min Range: -1.3937

Max Act: 1.3556. Min Act: -0.0000

Data Index: 1634209 (The Pile)

Max Activating Token Index: 954

Text #1

Max Range: 1.3937. Min Range: -1.3937

Max Act: 1.3408. Min Act: -0.0000

Data Index: 1881456 (The Pile)

Max Activating Token Index: 161

Text #2

Max Range: 1.3937. Min Range: -1.3937

Max Act: 1.3937. Min Act: -0.0000

Data Index: 1710552 (The Pile)

Max Activating Token Index: 639

Text #3

Max Range: 1.3937. Min Range: -1.3937

Max Act: 1.3312. Min Act: -0.0000

Data Index: 1610115 (The Pile)

Max Activating Token Index: 227

Text #4

Max Range: 1.3937. Min Range: -1.3937

Max Act: 1.2080. Min Act: -0.0000

Data Index: 1361964 (The Pile)

Max Activating Token Index: 442

Text #5

Max Range: 1.3937. Min Range: -1.3937

Max Act: 1.2240. Min Act: -0.0000

Data Index: 245208 (The Pile)

Max Activating Token Index: 356

Text #6

Max Range: 1.3937. Min Range: -1.3937

Max Act: 1.2238. Min Act: -0.0000

Data Index: 948145 (The Pile)

Max Activating Token Index: 205

Text #7

Max Range: 1.3937. Min Range: -1.3937

Max Act: 1.2551. Min Act: -0.0000

Data Index: 807965 (The Pile)

Max Activating Token Index: 643

Text #8

Max Range: 1.3937. Min Range: -1.3937

Max Act: 1.2561. Min Act: -0.0000

Data Index: 991667 (The Pile)

Max Activating Token Index: 62

Text #9

Max Range: 1.3937. Min Range: -1.3937

Max Act: 1.0955. Min Act: -0.0000

Data Index: 70912 (The Pile)

Max Activating Token Index: 73

Text #10

Max Range: 1.3937. Min Range: -1.3937

Max Act: 1.0442. Min Act: -0.0000

Data Index: 1616193 (The Pile)

Max Activating Token Index: 614

Text #11

Max Range: 1.3937. Min Range: -1.3937

Max Act: 1.0091. Min Act: -0.0000

Data Index: 1214027 (The Pile)

Max Activating Token Index: 258

Text #12

Max Range: 1.3937. Min Range: -1.3937

Max Act: 1.0959. Min Act: -0.0000

Data Index: 1113589 (The Pile)

Max Activating Token Index: 397

Text #13

Max Range: 1.3937. Min Range: -1.3937

Max Act: 1.1017. Min Act: -0.0000

Data Index: 626299 (The Pile)

Max Activating Token Index: 879

Text #14

Max Range: 1.3937. Min Range: -1.3937

Max Act: 1.0851. Min Act: -0.0000

Data Index: 1518285 (The Pile)

Max Activating Token Index: 398

Text #15

Max Range: 1.3937. Min Range: -1.3937

Max Act: 1.0240. Min Act: -0.0000

Data Index: 1222561 (The Pile)

Max Activating Token Index: 365

Text #16

Max Range: 1.3937. Min Range: -1.3937

Max Act: 1.1362. Min Act: -0.0000

Data Index: 188103 (The Pile)

Max Activating Token Index: 458

Text #17

Max Range: 1.3937. Min Range: -1.3937

Max Act: 1.0780. Min Act: -0.0000

Data Index: 672293 (The Pile)

Max Activating Token Index: 88

Text #18

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.9878. Min Act: -0.0000

Data Index: 1078587 (The Pile)

Max Activating Token Index: 97

Text #19

Max Range: 1.3937. Min Range: -1.3937

Max Act: 0.9736. Min Act: -0.0000

Data Index: 512443 (The Pile)

Max Activating Token Index: 959