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

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

Neuron 2615 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: 1.2134. Min Range: -1.2134

Max Act: 1.1700. Min Act: -0.0000

Data Index: 300681 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 1.2134. Min Range: -1.2134

Max Act: 1.2134. Min Act: -0.0000

Data Index: 861082 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 1.2134. Min Range: -1.2134

Max Act: 1.0016. Min Act: -0.0000

Data Index: 365175 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 1.2134. Min Range: -1.2134

Max Act: 1.0091. Min Act: -0.0000

Data Index: 583799 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.9614. Min Act: -0.0000

Data Index: 586802 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.9035. Min Act: -0.0000

Data Index: 315783 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.8902. Min Act: -0.0000

Data Index: 468634 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.8660. Min Act: -0.0000

Data Index: 983438 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.8665. Min Act: -0.0000

Data Index: 1334875 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.9305. Min Act: -0.0000

Data Index: 721577 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.8289. Min Act: -0.0000

Data Index: 1190168 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.7934. Min Act: -0.0000

Data Index: 1167003 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.8156. Min Act: -0.0000

Data Index: 1229609 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1601841 (Python Code)

Max Activating Token Index: 274

Text #14

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.7901. Min Act: -0.0000

Data Index: 238284 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.7367. Min Act: -0.0000

Data Index: 965836 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.7659. Min Act: -0.0000

Data Index: 1033627 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.7618. Min Act: -0.0000

Data Index: 20728 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.7010. Min Act: -0.0000

Data Index: 351734 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 1.2134. Min Range: -1.2134

Max Act: 0.7493. Min Act: -0.0000

Data Index: 934178 (C4 (Web Text))

Max Activating Token Index: 656