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

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

Neuron 3042 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: 3.4885. Min Range: -3.4885

Max Act: 3.3773. Min Act: -0.0001

Data Index: 1145880 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 3.4885. Min Range: -3.4885

Max Act: 3.4885. Min Act: -0.0001

Data Index: 106849 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 3.4885. Min Range: -3.4885

Max Act: 3.0253. Min Act: -0.0001

Data Index: 633078 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 3.4885. Min Range: -3.4885

Max Act: 2.9697. Min Act: -0.0001

Data Index: 71609 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 3.4885. Min Range: -3.4885

Max Act: 3.2233. Min Act: -0.0001

Data Index: 118524 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 3.4885. Min Range: -3.4885

Max Act: 3.2063. Min Act: -0.0001

Data Index: 711457 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 3.4885. Min Range: -3.4885

Max Act: 3.1345. Min Act: -0.0001

Data Index: 339821 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 3.4885. Min Range: -3.4885

Max Act: 2.8536. Min Act: -0.0001

Data Index: 1078045 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 3.4885. Min Range: -3.4885

Max Act: 2.9513. Min Act: -0.0001

Data Index: 139758 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 3.4885. Min Range: -3.4885

Max Act: 3.0606. Min Act: -0.0001

Data Index: 1038367 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 3.4885. Min Range: -3.4885

Max Act: 2.9283. Min Act: -0.0001

Data Index: 515537 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 3.4885. Min Range: -3.4885

Max Act: 2.9025. Min Act: -0.0001

Data Index: 1119282 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 3.4885. Min Range: -3.4885

Max Act: 2.8929. Min Act: -0.0001

Data Index: 31057 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 3.4885. Min Range: -3.4885

Max Act: 2.7166. Min Act: -0.0001

Data Index: 30838 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 3.4885. Min Range: -3.4885

Max Act: 2.8544. Min Act: -0.0001

Data Index: 548413 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 3.4885. Min Range: -3.4885

Max Act: 2.9768. Min Act: -0.0001

Data Index: 644686 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 3.4885. Min Range: -3.4885

Max Act: 2.8451. Min Act: -0.0001

Data Index: 391026 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 3.4885. Min Range: -3.4885

Max Act: 2.8282. Min Act: -0.0001

Data Index: 246060 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 3.4885. Min Range: -3.4885

Max Act: 2.7699. Min Act: -0.0001

Data Index: 290435 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 3.4885. Min Range: -3.4885

Max Act: 2.5138. Min Act: -0.0001

Data Index: 75545 (C4 (Web Text))

Max Activating Token Index: 444