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

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

Neuron 3460 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: 0.6843. Min Range: -0.6843

Max Act: 0.6843. Min Act: -0.0000

Data Index: 143546 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1157264 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.4085. Min Act: -0.0000

Data Index: 858475 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.3923. Min Act: -0.0000

Data Index: 1088778 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.3104. Min Act: -0.0001

Data Index: 608938 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1189813 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.2848. Min Act: -0.0000

Data Index: 307981 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.2947. Min Act: -0.0000

Data Index: 727399 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.2819. Min Act: -0.0000

Data Index: 1340019 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.2851. Min Act: -0.0000

Data Index: 560952 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.2853. Min Act: -0.0000

Data Index: 921290 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.2854. Min Act: -0.0000

Data Index: 361884 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1347051 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.2799. Min Act: -0.0000

Data Index: 480098 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.2850. Min Act: -0.0000

Data Index: 222411 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.2645. Min Act: -0.0000

Data Index: 729969 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1250796 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.2699. Min Act: -0.0000

Data Index: 400142 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.2606. Min Act: -0.0000

Data Index: 423700 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.2621. Min Act: -0.0000

Data Index: 1197755 (C4 (Web Text))

Max Activating Token Index: 809