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

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

Neuron 3503 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: 1.7154. Min Range: -1.7154

Max Act: 1.7154. Min Act: -0.0000

Data Index: 3274 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.6023. Min Act: -0.0000

Data Index: 867726 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.4964. Min Act: -0.0000

Data Index: 711245 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.3816. Min Act: -0.0000

Data Index: 321016 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.3715. Min Act: -0.0000

Data Index: 305531 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.3271. Min Act: -0.0000

Data Index: 961339 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.2423. Min Act: -0.0000

Data Index: 146168 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.2881. Min Act: -0.0000

Data Index: 1305666 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.2738. Min Act: -0.0000

Data Index: 691599 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.1951. Min Act: -0.0000

Data Index: 299426 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.1781. Min Act: -0.0000

Data Index: 785214 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.1733. Min Act: -0.0000

Data Index: 476025 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.1771. Min Act: -0.0000

Data Index: 586515 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.0237. Min Act: -0.0000

Data Index: 89376 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.0142. Min Act: -0.0000

Data Index: 690570 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.0555. Min Act: -0.0000

Data Index: 891399 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.0528. Min Act: -0.0000

Data Index: 307296 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.1112. Min Act: -0.0000

Data Index: 649903 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 1.7154. Min Range: -1.7154

Max Act: 0.9621. Min Act: -0.0000

Data Index: 1018170 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 1.7154. Min Range: -1.7154

Max Act: 1.0053. Min Act: -0.0000

Data Index: 1296413 (C4 (Web Text))

Max Activating Token Index: 11