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

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

Neuron 3344 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9835. Min Act: -0.0003

Data Index: 1168834 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9921. Min Act: -0.0003

Data Index: 954812 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8181. Min Act: -0.0003

Data Index: 1091203 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9391. Min Act: -0.0003

Data Index: 1289034 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9770. Min Act: -0.0003

Data Index: 1298379 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9322. Min Act: -0.0003

Data Index: 774376 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9050. Min Act: -0.0003

Data Index: 297998 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9889. Min Act: -0.0003

Data Index: 81127 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8710. Min Act: -0.0003

Data Index: 590209 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9132. Min Act: -0.0003

Data Index: 302590 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9367. Min Act: -0.0003

Data Index: 1011015 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8542. Min Act: -0.0003

Data Index: 643919 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8799. Min Act: -0.0003

Data Index: 1000635 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8580. Min Act: -0.0003

Data Index: 447432 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8499. Min Act: -0.0003

Data Index: 150199 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9315. Min Act: -0.0003

Data Index: 494416 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8993. Min Act: -0.0003

Data Index: 330630 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8949. Min Act: -0.0003

Data Index: 553758 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.7874. Min Act: -0.0003

Data Index: 110021 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8905. Min Act: -0.0003

Data Index: 668010 (C4 (Web Text))

Max Activating Token Index: 66