Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5302 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.2764. Min Act: -0.0000

Data Index: 1357292 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.6706. Min Act: -0.0000

Data Index: 93558 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.9164. Min Act: -0.0000

Data Index: 1250416 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.6393. Min Act: -0.0000

Data Index: 1158741 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.7397. Min Act: -0.0000

Data Index: 884066 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.6939. Min Act: -0.0000

Data Index: 4845 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.7021. Min Act: -0.0000

Data Index: 1310500 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.6483. Min Act: -0.0000

Data Index: 827146 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.6157. Min Act: -0.0000

Data Index: 789198 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.7263. Min Act: -0.0000

Data Index: 1264568 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.4261. Min Act: -0.0000

Data Index: 36392 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.4345. Min Act: -0.0000

Data Index: 514832 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.3935. Min Act: -0.0000

Data Index: 833126 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.3887. Min Act: -0.0000

Data Index: 1200394 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.5212. Min Act: -0.0000

Data Index: 651948 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.3628. Min Act: -0.0000

Data Index: 456308 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.2917. Min Act: -0.0000

Data Index: 537014 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.1581. Min Act: -0.0000

Data Index: 385926 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.2839. Min Act: -0.0000

Data Index: 1151261 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.2746. Min Act: -0.0000

Data Index: 192348 (C4 (Web Text))

Max Activating Token Index: 919