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

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

Neuron 1467 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.4740. Min Act: -0.0001

Data Index: 1105518 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.1730. Min Act: -0.0001

Data Index: 196153 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.0957. Min Act: -0.0001

Data Index: 939222 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.1057. Min Act: -0.0001

Data Index: 683458 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 3.4740. Min Range: -3.4740

Max Act: 2.9773. Min Act: -0.0001

Data Index: 361654 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 3.4740. Min Range: -3.4740

Max Act: 3.0111. Min Act: -0.0001

Data Index: 457963 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 3.4740. Min Range: -3.4740

Max Act: 2.7810. Min Act: -0.0001

Data Index: 402899 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 3.4740. Min Range: -3.4740

Max Act: 2.6202. Min Act: -0.0001

Data Index: 1170539 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 3.4740. Min Range: -3.4740

Max Act: 2.4345. Min Act: -0.0001

Data Index: 1149305 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 3.4740. Min Range: -3.4740

Max Act: 2.4660. Min Act: -0.0001

Data Index: 729743 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 3.4740. Min Range: -3.4740

Max Act: 2.3190. Min Act: -0.0001

Data Index: 496583 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 3.4740. Min Range: -3.4740

Max Act: 2.3767. Min Act: -0.0001

Data Index: 423424 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 3.4740. Min Range: -3.4740

Max Act: 2.3706. Min Act: -0.0001

Data Index: 578817 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 3.4740. Min Range: -3.4740

Max Act: 2.2474. Min Act: -0.0001

Data Index: 610555 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 3.4740. Min Range: -3.4740

Max Act: 2.4264. Min Act: -0.0001

Data Index: 401580 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 3.4740. Min Range: -3.4740

Max Act: 2.1892. Min Act: -0.0001

Data Index: 79018 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 3.4740. Min Range: -3.4740

Max Act: 2.1934. Min Act: -0.0001

Data Index: 1109385 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 3.4740. Min Range: -3.4740

Max Act: 2.1578. Min Act: -0.0001

Data Index: 516657 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 3.4740. Min Range: -3.4740

Max Act: 2.0273. Min Act: -0.0001

Data Index: 194403 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 3.4740. Min Range: -3.4740

Max Act: 2.0020. Min Act: -0.0001

Data Index: 1032473 (C4 (Web Text))

Max Activating Token Index: 208