Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4276 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4980. Min Range: -1.4980

Max Act: 1.4980. Min Act: -0.0002

Data Index: 307970 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 1.4980. Min Range: -1.4980

Max Act: 1.4505. Min Act: -0.0002

Data Index: 120168 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 1.4980. Min Range: -1.4980

Max Act: 1.3857. Min Act: -0.0002

Data Index: 747959 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 1.4980. Min Range: -1.4980

Max Act: 1.3007. Min Act: -0.0002

Data Index: 304658 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 1.4980. Min Range: -1.4980

Max Act: 1.3691. Min Act: -0.0002

Data Index: 514506 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 1.4980. Min Range: -1.4980

Max Act: 1.2903. Min Act: -0.0002

Data Index: 258130 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 1.4980. Min Range: -1.4980

Max Act: 1.3817. Min Act: -0.0002

Data Index: 1104326 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 1.4980. Min Range: -1.4980

Max Act: 1.2842. Min Act: -0.0002

Data Index: 240376 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 1.4980. Min Range: -1.4980

Max Act: 1.3537. Min Act: -0.0002

Data Index: 103224 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 1.4980. Min Range: -1.4980

Max Act: 1.3766. Min Act: -0.0002

Data Index: 691093 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 1.4980. Min Range: -1.4980

Max Act: 1.3423. Min Act: -0.0002

Data Index: 1173300 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 1.4980. Min Range: -1.4980

Max Act: 1.3247. Min Act: -0.0002

Data Index: 206723 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 1.4980. Min Range: -1.4980

Max Act: 1.2718. Min Act: -0.0002

Data Index: 1250758 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 1.4980. Min Range: -1.4980

Max Act: 1.2595. Min Act: -0.0002

Data Index: 622828 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 1.4980. Min Range: -1.4980

Max Act: 1.3038. Min Act: -0.0002

Data Index: 1086745 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 1.4980. Min Range: -1.4980

Max Act: 1.2677. Min Act: -0.0002

Data Index: 1330817 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 1.4980. Min Range: -1.4980

Max Act: 1.3285. Min Act: -0.0002

Data Index: 931054 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 1.4980. Min Range: -1.4980

Max Act: 1.2634. Min Act: -0.0002

Data Index: 807753 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 1.4980. Min Range: -1.4980

Max Act: 1.4054. Min Act: -0.0002

Data Index: 714815 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 1.4980. Min Range: -1.4980

Max Act: 1.3420. Min Act: -0.0002

Data Index: 1063555 (C4 (Web Text))

Max Activating Token Index: 780