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

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

Neuron 1664 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3617. Min Range: -2.3617

Max Act: 2.3617. Min Act: -0.0000

Data Index: 1327902 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 2.3617. Min Range: -2.3617

Max Act: 2.0937. Min Act: -0.0000

Data Index: 104390 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 2.3617. Min Range: -2.3617

Max Act: 2.1313. Min Act: -0.0000

Data Index: 1221388 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 2.3617. Min Range: -2.3617

Max Act: 1.8856. Min Act: -0.0000

Data Index: 1276730 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 2.3617. Min Range: -2.3617

Max Act: 1.7795. Min Act: -0.0000

Data Index: 934219 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 2.3617. Min Range: -2.3617

Max Act: 1.7093. Min Act: -0.0000

Data Index: 289809 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 2.3617. Min Range: -2.3617

Max Act: 1.7130. Min Act: -0.0000

Data Index: 401479 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 2.3617. Min Range: -2.3617

Max Act: 1.6761. Min Act: -0.0000

Data Index: 151501 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 2.3617. Min Range: -2.3617

Max Act: 1.6748. Min Act: -0.0000

Data Index: 971338 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 2.3617. Min Range: -2.3617

Max Act: 1.6314. Min Act: -0.0000

Data Index: 90678 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 2.3617. Min Range: -2.3617

Max Act: 1.6928. Min Act: -0.0000

Data Index: 1152743 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 2.3617. Min Range: -2.3617

Max Act: 1.5912. Min Act: -0.0000

Data Index: 589225 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 2.3617. Min Range: -2.3617

Max Act: 1.5752. Min Act: -0.0000

Data Index: 116173 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 2.3617. Min Range: -2.3617

Max Act: 1.5183. Min Act: -0.0000

Data Index: 398980 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 2.3617. Min Range: -2.3617

Max Act: 1.5590. Min Act: -0.0000

Data Index: 1025996 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 2.3617. Min Range: -2.3617

Max Act: 1.5586. Min Act: -0.0000

Data Index: 685004 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 2.3617. Min Range: -2.3617

Max Act: 1.4439. Min Act: -0.0000

Data Index: 341371 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 2.3617. Min Range: -2.3617

Max Act: 1.5701. Min Act: -0.0000

Data Index: 498395 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 2.3617. Min Range: -2.3617

Max Act: 1.5057. Min Act: -0.0000

Data Index: 984138 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 2.3617. Min Range: -2.3617

Max Act: 1.5018. Min Act: -0.0000

Data Index: 175703 (C4 (Web Text))

Max Activating Token Index: 770