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

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

Neuron 5038 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4348. Min Range: -2.4348

Max Act: 2.4348. Min Act: -0.0000

Data Index: 874153 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 2.4348. Min Range: -2.4348

Max Act: 2.2540. Min Act: -0.0000

Data Index: 1039977 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 2.4348. Min Range: -2.4348

Max Act: 1.8999. Min Act: -0.0000

Data Index: 998246 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 2.4348. Min Range: -2.4348

Max Act: 1.8442. Min Act: -0.0000

Data Index: 51010 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 2.4348. Min Range: -2.4348

Max Act: 1.8917. Min Act: -0.0000

Data Index: 1286281 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 2.4348. Min Range: -2.4348

Max Act: 1.7789. Min Act: -0.0000

Data Index: 599556 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 2.4348. Min Range: -2.4348

Max Act: 1.5434. Min Act: -0.0000

Data Index: 164349 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 2.4348. Min Range: -2.4348

Max Act: 1.5276. Min Act: -0.0000

Data Index: 78223 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 2.4348. Min Range: -2.4348

Max Act: 1.6066. Min Act: -0.0000

Data Index: 1057439 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 2.4348. Min Range: -2.4348

Max Act: 1.4134. Min Act: -0.0000

Data Index: 90704 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 2.4348. Min Range: -2.4348

Max Act: 1.4672. Min Act: -0.0000

Data Index: 818045 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 2.4348. Min Range: -2.4348

Max Act: 1.3023. Min Act: -0.0000

Data Index: 336957 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 2.4348. Min Range: -2.4348

Max Act: 1.4073. Min Act: -0.0000

Data Index: 970945 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 2.4348. Min Range: -2.4348

Max Act: 1.3049. Min Act: -0.0000

Data Index: 1094490 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 2.4348. Min Range: -2.4348

Max Act: 1.2308. Min Act: -0.0000

Data Index: 362742 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 2.4348. Min Range: -2.4348

Max Act: 1.2218. Min Act: -0.0000

Data Index: 122525 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 2.4348. Min Range: -2.4348

Max Act: 1.1531. Min Act: -0.0000

Data Index: 31851 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 2.4348. Min Range: -2.4348

Max Act: 1.2119. Min Act: -0.0000

Data Index: 1270661 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 2.4348. Min Range: -2.4348

Max Act: 1.2144. Min Act: -0.0000

Data Index: 1349372 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 2.4348. Min Range: -2.4348

Max Act: 1.1321. Min Act: -0.0000

Data Index: 1217830 (C4 (Web Text))

Max Activating Token Index: 619