Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3276 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.1455. Min Range: -6.1455

Max Act: 6.1455. Min Act: -0.0000

Data Index: 301377 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.7553. Min Act: -0.0000

Data Index: 704430 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.9071. Min Act: -0.0000

Data Index: 766388 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.3033. Min Act: -0.0000

Data Index: 1166340 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.3058. Min Act: -0.0000

Data Index: 1042545 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.4709. Min Act: -0.0000

Data Index: 1234546 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.1277. Min Act: -0.0000

Data Index: 835184 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 6.1455. Min Range: -6.1455

Max Act: 4.9094. Min Act: -0.0000

Data Index: 821169 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.2776. Min Act: -0.0000

Data Index: 251192 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.1206. Min Act: -0.0000

Data Index: 11617 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 6.1455. Min Range: -6.1455

Max Act: 5.0093. Min Act: -0.0000

Data Index: 1209436 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 6.1455. Min Range: -6.1455

Max Act: 4.8464. Min Act: -0.0000

Data Index: 492217 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 6.1455. Min Range: -6.1455

Max Act: 4.5624. Min Act: -0.0000

Data Index: 1103324 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 6.1455. Min Range: -6.1455

Max Act: 4.4792. Min Act: -0.0000

Data Index: 1072217 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 6.1455. Min Range: -6.1455

Max Act: 4.5765. Min Act: -0.0000

Data Index: 888538 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 6.1455. Min Range: -6.1455

Max Act: 4.7688. Min Act: -0.0000

Data Index: 216108 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 6.1455. Min Range: -6.1455

Max Act: 4.7487. Min Act: -0.0000

Data Index: 1259964 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 6.1455. Min Range: -6.1455

Max Act: 4.5326. Min Act: -0.0000

Data Index: 778308 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 6.1455. Min Range: -6.1455

Max Act: 4.3518. Min Act: -0.0000

Data Index: 938392 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 6.1455. Min Range: -6.1455

Max Act: 4.4740. Min Act: -0.0000

Data Index: 68813 (C4 (Web Text))

Max Activating Token Index: 257