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

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

Neuron 610 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2465. Min Range: -0.2465

Max Act: 0.2465. Min Act: -0.0001

Data Index: 717037 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.2465. Min Range: -0.2465

Max Act: 0.2402. Min Act: -0.0001

Data Index: 793814 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.2465. Min Range: -0.2465

Max Act: 0.2301. Min Act: -0.0001

Data Index: 980998 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.2465. Min Range: -0.2465

Max Act: 0.2367. Min Act: -0.0001

Data Index: 311754 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.2465. Min Range: -0.2465

Max Act: 0.2232. Min Act: -0.0001

Data Index: 23700 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.2465. Min Range: -0.2465

Max Act: 0.2147. Min Act: -0.0001

Data Index: 332587 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.2465. Min Range: -0.2465

Max Act: 0.2091. Min Act: -0.0001

Data Index: 1300449 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.2465. Min Range: -0.2465

Max Act: 0.2054. Min Act: -0.0001

Data Index: 800863 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.2465. Min Range: -0.2465

Max Act: 0.1957. Min Act: -0.0001

Data Index: 122896 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.2465. Min Range: -0.2465

Max Act: 0.1946. Min Act: -0.0001

Data Index: 1334170 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 0.2465. Min Range: -0.2465

Max Act: 0.1986. Min Act: -0.0001

Data Index: 1061618 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.2465. Min Range: -0.2465

Max Act: 0.1922. Min Act: -0.0001

Data Index: 387900 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.2465. Min Range: -0.2465

Max Act: 0.2044. Min Act: -0.0001

Data Index: 717705 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.2465. Min Range: -0.2465

Max Act: 0.1929. Min Act: -0.0001

Data Index: 219396 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.2465. Min Range: -0.2465

Max Act: 0.1680. Min Act: -0.0001

Data Index: 127741 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.2465. Min Range: -0.2465

Max Act: 0.1896. Min Act: -0.0001

Data Index: 985578 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.2465. Min Range: -0.2465

Max Act: 0.1886. Min Act: -0.0001

Data Index: 822433 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.2465. Min Range: -0.2465

Max Act: 0.2009. Min Act: -0.0001

Data Index: 2660 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 0.2465. Min Range: -0.2465

Max Act: 0.1813. Min Act: -0.0001

Data Index: 658656 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.2465. Min Range: -0.2465

Max Act: 0.1894. Min Act: -0.0001

Data Index: 1163702 (C4 (Web Text))

Max Activating Token Index: 436