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

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

Neuron 4807 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4636. Min Act: -0.0000

Data Index: 75850 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4421. Min Act: -0.0000

Data Index: 622874 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.4009. Min Act: -0.0000

Data Index: 1122123 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3815. Min Act: -0.0000

Data Index: 1004454 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3677. Min Act: -0.0000

Data Index: 638821 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3725. Min Act: -0.0000

Data Index: 437728 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3693. Min Act: -0.0000

Data Index: 500702 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3418. Min Act: -0.0000

Data Index: 1104356 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3482. Min Act: -0.0000

Data Index: 1329950 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3448. Min Act: -0.0000

Data Index: 36687 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3425. Min Act: -0.0000

Data Index: 57629 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3408. Min Act: -0.0000

Data Index: 937652 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3263. Min Act: 0.0000

Data Index: 138747 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3297. Min Act: 0.0000

Data Index: 1273320 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1000340 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3246. Min Act: -0.0000

Data Index: 773765 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3350. Min Act: -0.0000

Data Index: 442090 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3242. Min Act: -0.0000

Data Index: 380609 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3145. Min Act: -0.0000

Data Index: 716782 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.4636. Min Range: -0.4636

Max Act: 0.3137. Min Act: -0.0000

Data Index: 902666 (C4 (Web Text))

Max Activating Token Index: 526