Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 436 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4946. Min Act: -0.0001

Data Index: 727103 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4410. Min Act: -0.0001

Data Index: 741033 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4018. Min Act: -0.0001

Data Index: 545231 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4547. Min Act: -0.0001

Data Index: 372503 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3923. Min Act: -0.0001

Data Index: 743437 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4129. Min Act: -0.0001

Data Index: 545398 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4066. Min Act: -0.0001

Data Index: 493115 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4098. Min Act: -0.0001

Data Index: 478551 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3816. Min Act: -0.0001

Data Index: 842274 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3799. Min Act: -0.0001

Data Index: 1214275 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3918. Min Act: -0.0001

Data Index: 549754 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3795. Min Act: -0.0001

Data Index: 249885 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4207. Min Act: -0.0001

Data Index: 478235 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3625. Min Act: -0.0001

Data Index: 911314 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3922. Min Act: -0.0001

Data Index: 1274534 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3768. Min Act: -0.0001

Data Index: 547915 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3776. Min Act: -0.0001

Data Index: 660019 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3789. Min Act: -0.0001

Data Index: 196982 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3650. Min Act: -0.0001

Data Index: 544715 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3868. Min Act: -0.0001

Data Index: 1202279 (C4 (Web Text))

Max Activating Token Index: 366