Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 844 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3465. Min Act: -0.0001

Data Index: 263228 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3717. Min Act: -0.0001

Data Index: 1071200 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.4032. Min Act: -0.0001

Data Index: 958161 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3367. Min Act: -0.0001

Data Index: 676633 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3501. Min Act: -0.0001

Data Index: 962844 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3216. Min Act: -0.0001

Data Index: 779381 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3274. Min Act: -0.0001

Data Index: 656830 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3049. Min Act: -0.0001

Data Index: 951058 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3076. Min Act: -0.0001

Data Index: 543981 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3333. Min Act: -0.0001

Data Index: 288380 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2919. Min Act: -0.0001

Data Index: 1211560 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2702. Min Act: -0.0001

Data Index: 1032793 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2998. Min Act: -0.0001

Data Index: 20500 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2894. Min Act: -0.0001

Data Index: 285597 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2922. Min Act: -0.0001

Data Index: 232367 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2667. Min Act: -0.0001

Data Index: 384024 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2975. Min Act: -0.0001

Data Index: 675783 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3125. Min Act: -0.0001

Data Index: 29377 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2804. Min Act: -0.0001

Data Index: 278078 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2570. Min Act: -0.0001

Data Index: 319457 (C4 (Web Text))

Max Activating Token Index: 142