Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3750 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.9918. Min Act: -0.0000

Data Index: 296774 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.7681. Min Act: -0.0000

Data Index: 756639 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.6956. Min Act: -0.0000

Data Index: 325223 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.4074. Min Act: -0.0000

Data Index: 677519 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.3382. Min Act: -0.0000

Data Index: 382726 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.2028. Min Act: -0.0000

Data Index: 1237566 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.0960. Min Act: -0.0000

Data Index: 91019 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.0808. Min Act: -0.0000

Data Index: 1303113 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 2.9918. Min Range: -2.9918

Max Act: 1.9807. Min Act: -0.0000

Data Index: 916578 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 2.9918. Min Range: -2.9918

Max Act: 2.0887. Min Act: -0.0000

Data Index: 1145324 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 2.9918. Min Range: -2.9918

Max Act: 1.9853. Min Act: -0.0000

Data Index: 588420 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 2.9918. Min Range: -2.9918

Max Act: 1.5624. Min Act: -0.0000

Data Index: 26102 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 2.9918. Min Range: -2.9918

Max Act: 1.7632. Min Act: -0.0000

Data Index: 1447276 (Python Code)

Max Activating Token Index: 311

Text #13

Max Range: 2.9918. Min Range: -2.9918

Max Act: 1.6424. Min Act: -0.0000

Data Index: 75518 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 2.9918. Min Range: -2.9918

Max Act: 1.5375. Min Act: -0.0000

Data Index: 606006 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 2.9918. Min Range: -2.9918

Max Act: 1.5060. Min Act: 0.0000

Data Index: 844502 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 2.9918. Min Range: -2.9918

Max Act: 1.4310. Min Act: -0.0000

Data Index: 1406767 (Python Code)

Max Activating Token Index: 282

Text #17

Max Range: 2.9918. Min Range: -2.9918

Max Act: 1.4611. Min Act: -0.0000

Data Index: 246931 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 2.9918. Min Range: -2.9918

Max Act: 1.4192. Min Act: -0.0000

Data Index: 1052180 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 2.9918. Min Range: -2.9918

Max Act: 1.3731. Min Act: -0.0000

Data Index: 328872 (C4 (Web Text))

Max Activating Token Index: 492