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

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

Neuron 5069 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.3192. Min Act: -0.0000

Data Index: 689985 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.3204. Min Act: -0.0001

Data Index: 458615 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2976. Min Act: -0.0000

Data Index: 123606 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2961. Min Act: -0.0000

Data Index: 1293617 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2962. Min Act: -0.0000

Data Index: 1263273 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2845. Min Act: -0.0000

Data Index: 805 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1207794 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2786. Min Act: -0.0000

Data Index: 943045 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2800. Min Act: -0.0000

Data Index: 990758 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2632. Min Act: -0.0000

Data Index: 279820 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1274250 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1305633 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2655. Min Act: -0.0000

Data Index: 901896 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2633. Min Act: -0.0000

Data Index: 657314 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1175517 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2481. Min Act: -0.0000

Data Index: 533085 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2517. Min Act: -0.0000

Data Index: 722481 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2528. Min Act: -0.0000

Data Index: 411830 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1221887 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2563. Min Act: -0.0000

Data Index: 290190 (C4 (Web Text))

Max Activating Token Index: 834