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

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

Neuron 3510 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: 0.3348. Min Range: -0.3348

Max Act: 0.3267. Min Act: -0.0002

Data Index: 1001166 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.3348. Min Act: -0.0002

Data Index: 979507 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.3171. Min Act: -0.0002

Data Index: 689069 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.3276. Min Act: -0.0002

Data Index: 1011372 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.3025. Min Act: -0.0002

Data Index: 941628 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.3184. Min Act: -0.0002

Data Index: 1321165 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.3081. Min Act: -0.0002

Data Index: 750097 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.3048. Min Act: -0.0002

Data Index: 104141 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2711. Min Act: -0.0002

Data Index: 258057 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.3039. Min Act: -0.0002

Data Index: 1257139 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2764. Min Act: -0.0002

Data Index: 393608 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2917. Min Act: -0.0002

Data Index: 352689 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2953. Min Act: -0.0002

Data Index: 1278319 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2959. Min Act: -0.0002

Data Index: 1134130 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.3007. Min Act: -0.0002

Data Index: 1351154 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2776. Min Act: -0.0002

Data Index: 1284606 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2665. Min Act: -0.0002

Data Index: 458548 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.3072. Min Act: -0.0002

Data Index: 656141 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2639. Min Act: -0.0002

Data Index: 897261 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2998. Min Act: -0.0002

Data Index: 424323 (C4 (Web Text))

Max Activating Token Index: 470