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

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

Neuron 2642 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: 3.3246. Min Range: -3.3246

Max Act: 3.3246. Min Act: -0.0001

Data Index: 333170 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 3.3246. Min Range: -3.3246

Max Act: 3.0570. Min Act: -0.0001

Data Index: 983367 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 3.3246. Min Range: -3.3246

Max Act: 2.7476. Min Act: -0.0001

Data Index: 376895 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 3.3246. Min Range: -3.3246

Max Act: 2.6137. Min Act: -0.0001

Data Index: 4089 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 3.3246. Min Range: -3.3246

Max Act: 2.4680. Min Act: -0.0001

Data Index: 521724 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 3.3246. Min Range: -3.3246

Max Act: 2.4261. Min Act: -0.0001

Data Index: 987063 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 3.3246. Min Range: -3.3246

Max Act: 2.5060. Min Act: -0.0001

Data Index: 313860 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 3.3246. Min Range: -3.3246

Max Act: 2.1660. Min Act: -0.0001

Data Index: 965689 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 3.3246. Min Range: -3.3246

Max Act: 2.6564. Min Act: -0.0001

Data Index: 835915 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 3.3246. Min Range: -3.3246

Max Act: 2.5030. Min Act: -0.0001

Data Index: 480761 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 3.3246. Min Range: -3.3246

Max Act: 2.2885. Min Act: -0.0001

Data Index: 350678 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 3.3246. Min Range: -3.3246

Max Act: 2.3931. Min Act: -0.0001

Data Index: 808829 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 3.3246. Min Range: -3.3246

Max Act: 2.2449. Min Act: -0.0001

Data Index: 1111512 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 3.3246. Min Range: -3.3246

Max Act: 2.2136. Min Act: -0.0001

Data Index: 331424 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 3.3246. Min Range: -3.3246

Max Act: 2.3101. Min Act: -0.0001

Data Index: 883724 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 3.3246. Min Range: -3.3246

Max Act: 2.3227. Min Act: -0.0001

Data Index: 318589 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 3.3246. Min Range: -3.3246

Max Act: 2.1992. Min Act: -0.0001

Data Index: 1197027 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 3.3246. Min Range: -3.3246

Max Act: 2.4097. Min Act: -0.0001

Data Index: 947514 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 3.3246. Min Range: -3.3246

Max Act: 2.1526. Min Act: -0.0001

Data Index: 888391 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 3.3246. Min Range: -3.3246

Max Act: 2.2561. Min Act: -0.0001

Data Index: 1120829 (C4 (Web Text))

Max Activating Token Index: 38