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

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

Neuron 1562 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.3310. Min Act: -0.0001

Data Index: 1212335 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2991. Min Act: -0.0001

Data Index: 123228 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2937. Min Act: -0.0001

Data Index: 34816 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2983. Min Act: -0.0001

Data Index: 897741 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2826. Min Act: -0.0001

Data Index: 1282375 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2893. Min Act: -0.0001

Data Index: 809325 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2671. Min Act: -0.0001

Data Index: 3659 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2754. Min Act: -0.0001

Data Index: 966351 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2656. Min Act: -0.0001

Data Index: 78135 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2736. Min Act: -0.0001

Data Index: 1332634 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2718. Min Act: -0.0001

Data Index: 357097 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2781. Min Act: -0.0001

Data Index: 245017 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2690. Min Act: -0.0001

Data Index: 1017698 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2669. Min Act: -0.0001

Data Index: 595648 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2672. Min Act: -0.0001

Data Index: 366742 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2557. Min Act: -0.0001

Data Index: 685949 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2667. Min Act: -0.0001

Data Index: 1210513 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2721. Min Act: -0.0001

Data Index: 847337 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2521. Min Act: -0.0001

Data Index: 369625 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2711. Min Act: -0.0001

Data Index: 448992 (C4 (Web Text))

Max Activating Token Index: 750