Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2173 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3891. Min Act: -0.0001

Data Index: 349745 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3622. Min Act: -0.0000

Data Index: 870391 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2861. Min Act: -0.0000

Data Index: 376136 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3322. Min Act: -0.0001

Data Index: 1189760 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3016. Min Act: -0.0001

Data Index: 1021752 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2863. Min Act: -0.0000

Data Index: 831548 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2840. Min Act: -0.0000

Data Index: 278169 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3112. Min Act: -0.0001

Data Index: 1354493 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3001. Min Act: -0.0001

Data Index: 189469 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2832. Min Act: -0.0001

Data Index: 59725 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1140647 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2904. Min Act: -0.0001

Data Index: 628709 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3039. Min Act: -0.0001

Data Index: 55945 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2814. Min Act: -0.0001

Data Index: 1272257 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2681. Min Act: -0.0000

Data Index: 734054 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2809. Min Act: -0.0001

Data Index: 325217 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2692. Min Act: -0.0001

Data Index: 227020 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2780. Min Act: -0.0000

Data Index: 1117746 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2588. Min Act: -0.0001

Data Index: 637958 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2678. Min Act: -0.0000

Data Index: 928482 (C4 (Web Text))

Max Activating Token Index: 511