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

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

Neuron 3081 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.3198. Min Act: -0.0001

Data Index: 990758 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.4348. Min Act: -0.0001

Data Index: 51929 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2890. Min Act: -0.0001

Data Index: 1060166 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.4036. Min Act: -0.0001

Data Index: 264250 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.3631. Min Act: -0.0001

Data Index: 908573 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.3882. Min Act: -0.0001

Data Index: 391399 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.3571. Min Act: -0.0001

Data Index: 980936 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2585. Min Act: -0.0001

Data Index: 284733 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2367. Min Act: -0.0001

Data Index: 1046333 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.1348. Min Act: -0.0001

Data Index: 377923 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.1918. Min Act: -0.0001

Data Index: 977253 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.0806. Min Act: -0.0001

Data Index: 339744 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.1304. Min Act: -0.0001

Data Index: 1291718 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2519. Min Act: -0.0001

Data Index: 76273 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.3521. Min Act: -0.0001

Data Index: 1162039 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.1991. Min Act: -0.0001

Data Index: 904292 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.3315. Min Act: -0.0001

Data Index: 361289 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.2486. Min Act: -0.0001

Data Index: 238921 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.1401. Min Act: -0.0001

Data Index: 537031 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 1.4348. Min Range: -1.4348

Max Act: 1.1123. Min Act: -0.0001

Data Index: 1015574 (C4 (Web Text))

Max Activating Token Index: 674