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

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

Neuron 3182 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5312. Min Range: -2.5312

Max Act: 2.3294. Min Act: -0.0000

Data Index: 729537 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 2.5312. Min Range: -2.5312

Max Act: 2.4349. Min Act: -0.0000

Data Index: 597259 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 2.5312. Min Range: -2.5312

Max Act: 2.5312. Min Act: -0.0000

Data Index: 557570 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 2.5312. Min Range: -2.5312

Max Act: 2.3967. Min Act: -0.0000

Data Index: 250704 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 2.5312. Min Range: -2.5312

Max Act: 2.1536. Min Act: -0.0000

Data Index: 1099045 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 2.5312. Min Range: -2.5312

Max Act: 2.2125. Min Act: -0.0000

Data Index: 88338 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 2.5312. Min Range: -2.5312

Max Act: 2.4011. Min Act: -0.0000

Data Index: 809132 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 2.5312. Min Range: -2.5312

Max Act: 2.0544. Min Act: -0.0000

Data Index: 69736 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 2.5312. Min Range: -2.5312

Max Act: 1.8980. Min Act: -0.0000

Data Index: 1306613 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 2.5312. Min Range: -2.5312

Max Act: 1.9667. Min Act: -0.0000

Data Index: 995681 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 2.5312. Min Range: -2.5312

Max Act: 1.8421. Min Act: -0.0000

Data Index: 292938 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 2.5312. Min Range: -2.5312

Max Act: 1.6809. Min Act: -0.0000

Data Index: 664062 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 2.5312. Min Range: -2.5312

Max Act: 1.6361. Min Act: -0.0000

Data Index: 566482 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 2.5312. Min Range: -2.5312

Max Act: 1.7211. Min Act: -0.0000

Data Index: 17802 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 2.5312. Min Range: -2.5312

Max Act: 1.6209. Min Act: -0.0000

Data Index: 1187516 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 2.5312. Min Range: -2.5312

Max Act: 1.7738. Min Act: -0.0000

Data Index: 570948 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 2.5312. Min Range: -2.5312

Max Act: 1.6328. Min Act: -0.0000

Data Index: 1106755 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 2.5312. Min Range: -2.5312

Max Act: 1.6243. Min Act: -0.0000

Data Index: 334141 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 2.5312. Min Range: -2.5312

Max Act: 1.5924. Min Act: -0.0000

Data Index: 911494 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 2.5312. Min Range: -2.5312

Max Act: 1.5039. Min Act: -0.0000

Data Index: 202999 (C4 (Web Text))

Max Activating Token Index: 245