Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1248 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3139. Min Range: -1.3139

Max Act: 1.3139. Min Act: -0.0003

Data Index: 362544 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 1.3139. Min Range: -1.3139

Max Act: 1.1790. Min Act: -0.0003

Data Index: 1077614 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 1.3139. Min Range: -1.3139

Max Act: 1.0868. Min Act: -0.0003

Data Index: 864201 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 1.3139. Min Range: -1.3139

Max Act: 1.1057. Min Act: -0.0003

Data Index: 396640 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 1.3139. Min Range: -1.3139

Max Act: 1.0408. Min Act: -0.0003

Data Index: 1008530 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 1.3139. Min Range: -1.3139

Max Act: 1.1199. Min Act: -0.0003

Data Index: 348410 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.9961. Min Act: -0.0003

Data Index: 135111 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.9515. Min Act: -0.0003

Data Index: 195647 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.9962. Min Act: -0.0003

Data Index: 1157561 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.9668. Min Act: -0.0003

Data Index: 545503 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.9104. Min Act: -0.0003

Data Index: 33232 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 1.3139. Min Range: -1.3139

Max Act: 1.0158. Min Act: -0.0003

Data Index: 768560 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.9365. Min Act: -0.0003

Data Index: 632720 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.8950. Min Act: -0.0003

Data Index: 5565 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.8399. Min Act: -0.0003

Data Index: 368079 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.9331. Min Act: -0.0003

Data Index: 769744 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.8759. Min Act: -0.0003

Data Index: 880007 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.7770. Min Act: -0.0003

Data Index: 474577 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.9045. Min Act: -0.0003

Data Index: 985389 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 1.3139. Min Range: -1.3139

Max Act: 0.8975. Min Act: -0.0003

Data Index: 1036129 (C4 (Web Text))

Max Activating Token Index: 276