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

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

Neuron 2479 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.5070. Min Act: -0.0000

Data Index: 555469 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.0446. Min Act: -0.0001

Data Index: 893248 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.1837. Min Act: -0.0001

Data Index: 606018 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.2942. Min Act: -0.0000

Data Index: 576281 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.2053. Min Act: -0.0001

Data Index: 1067034 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.0283. Min Act: -0.0000

Data Index: 1267875 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.2770. Min Act: -0.0001

Data Index: 1212754 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.1336. Min Act: -0.0000

Data Index: 663754 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.2856. Min Act: -0.0001

Data Index: 515586 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 3.5070. Min Range: -3.5070

Max Act: 2.9946. Min Act: -0.0001

Data Index: 865381 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.1330. Min Act: -0.0001

Data Index: 7990 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 3.5070. Min Range: -3.5070

Max Act: 2.8636. Min Act: -0.0000

Data Index: 334460 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.2213. Min Act: -0.0001

Data Index: 613269 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 3.5070. Min Range: -3.5070

Max Act: 2.9619. Min Act: -0.0000

Data Index: 142893 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.3269. Min Act: -0.0001

Data Index: 597429 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 3.5070. Min Range: -3.5070

Max Act: 2.7892. Min Act: -0.0000

Data Index: 1283317 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 3.5070. Min Range: -3.5070

Max Act: 2.9273. Min Act: -0.0000

Data Index: 980327 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 3.5070. Min Range: -3.5070

Max Act: 2.8369. Min Act: -0.0000

Data Index: 1249008 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 3.5070. Min Range: -3.5070

Max Act: 2.8599. Min Act: -0.0000

Data Index: 335114 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 3.5070. Min Range: -3.5070

Max Act: 2.4565. Min Act: -0.0001

Data Index: 109563 (C4 (Web Text))

Max Activating Token Index: 868