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

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

Neuron 2842 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2089. Min Range: -6.2089

Max Act: 6.2089. Min Act: -0.0000

Data Index: 1235117 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 6.2089. Min Range: -6.2089

Max Act: 5.9862. Min Act: -0.0000

Data Index: 490495 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 6.2089. Min Range: -6.2089

Max Act: 5.9226. Min Act: -0.0000

Data Index: 373485 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 6.2089. Min Range: -6.2089

Max Act: 5.8608. Min Act: -0.0000

Data Index: 822733 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 6.2089. Min Range: -6.2089

Max Act: 5.7060. Min Act: -0.0000

Data Index: 1359665 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 6.2089. Min Range: -6.2089

Max Act: 5.6548. Min Act: -0.0000

Data Index: 1175768 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 6.2089. Min Range: -6.2089

Max Act: 5.5861. Min Act: -0.0000

Data Index: 74285 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 6.2089. Min Range: -6.2089

Max Act: 5.3731. Min Act: -0.0000

Data Index: 131381 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 6.2089. Min Range: -6.2089

Max Act: 5.3437. Min Act: -0.0000

Data Index: 1116542 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 6.2089. Min Range: -6.2089

Max Act: 5.4814. Min Act: -0.0000

Data Index: 359106 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 6.2089. Min Range: -6.2089

Max Act: 5.4652. Min Act: -0.0000

Data Index: 1105229 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 6.2089. Min Range: -6.2089

Max Act: 5.6298. Min Act: -0.0000

Data Index: 356460 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 6.2089. Min Range: -6.2089

Max Act: 5.4303. Min Act: -0.0000

Data Index: 334896 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 6.2089. Min Range: -6.2089

Max Act: 5.1074. Min Act: -0.0000

Data Index: 924856 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 6.2089. Min Range: -6.2089

Max Act: 5.2936. Min Act: -0.0000

Data Index: 95043 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 6.2089. Min Range: -6.2089

Max Act: 5.0367. Min Act: -0.0000

Data Index: 1256305 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 6.2089. Min Range: -6.2089

Max Act: 5.1737. Min Act: -0.0000

Data Index: 1084431 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 6.2089. Min Range: -6.2089

Max Act: 4.9957. Min Act: -0.0000

Data Index: 247149 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 6.2089. Min Range: -6.2089

Max Act: 5.1166. Min Act: -0.0000

Data Index: 188529 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 6.2089. Min Range: -6.2089

Max Act: 5.1065. Min Act: -0.0000

Data Index: 407725 (C4 (Web Text))

Max Activating Token Index: 180