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

Dataset: The Pile

Neuron 1142 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: 0.4098. Min Range: -0.4098

Max Act: 0.3560. Min Act: -0.0000

Data Index: 169733 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3912. Min Act: -0.0000

Data Index: 913670 (The Pile)

Max Activating Token Index: 526

Text #2

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3360. Min Act: -0.0000

Data Index: 1757365 (The Pile)

Max Activating Token Index: 785

Text #3

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.4098. Min Act: -0.0000

Data Index: 443104 (The Pile)

Max Activating Token Index: 716

Text #4

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3064. Min Act: -0.0000

Data Index: 970384 (The Pile)

Max Activating Token Index: 926

Text #5

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3518. Min Act: -0.0000

Data Index: 1652708 (The Pile)

Max Activating Token Index: 304

Text #6

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3237. Min Act: -0.0000

Data Index: 740776 (The Pile)

Max Activating Token Index: 373

Text #7

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3291. Min Act: -0.0000

Data Index: 1270686 (The Pile)

Max Activating Token Index: 145

Text #8

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3503. Min Act: -0.0000

Data Index: 1467823 (The Pile)

Max Activating Token Index: 389

Text #9

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3161. Min Act: -0.0000

Data Index: 1996956 (The Pile)

Max Activating Token Index: 700

Text #10

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3242. Min Act: -0.0000

Data Index: 1773161 (The Pile)

Max Activating Token Index: 644

Text #11

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2882. Min Act: -0.0000

Data Index: 261471 (The Pile)

Max Activating Token Index: 711

Text #12

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1605144 (The Pile)

Max Activating Token Index: 753

Text #13

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3013. Min Act: -0.0000

Data Index: 1741333 (The Pile)

Max Activating Token Index: 164

Text #14

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2967. Min Act: -0.0000

Data Index: 235126 (The Pile)

Max Activating Token Index: 17

Text #15

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2897. Min Act: -0.0000

Data Index: 455288 (The Pile)

Max Activating Token Index: 513

Text #16

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2726. Min Act: -0.0000

Data Index: 260066 (The Pile)

Max Activating Token Index: 704

Text #17

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2843. Min Act: -0.0000

Data Index: 739349 (The Pile)

Max Activating Token Index: 919

Text #18

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.2638. Min Act: -0.0000

Data Index: 537461 (The Pile)

Max Activating Token Index: 400

Text #19

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3007. Min Act: -0.0000

Data Index: 1330237 (The Pile)

Max Activating Token Index: 237