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

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

Neuron 725 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1236. Min Range: -3.1236

Max Act: 3.1236. Min Act: -0.0000

Data Index: 512275 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 3.1236. Min Range: -3.1236

Max Act: 2.0193. Min Act: -0.0000

Data Index: 1347011 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 3.1236. Min Range: -3.1236

Max Act: 2.0071. Min Act: -0.0000

Data Index: 1286810 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 3.1236. Min Range: -3.1236

Max Act: 1.9065. Min Act: -0.0000

Data Index: 955755 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 3.1236. Min Range: -3.1236

Max Act: 1.8458. Min Act: -0.0000

Data Index: 139459 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 3.1236. Min Range: -3.1236

Max Act: 1.7597. Min Act: -0.0000

Data Index: 60803 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 3.1236. Min Range: -3.1236

Max Act: 1.5623. Min Act: -0.0000

Data Index: 646152 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 3.1236. Min Range: -3.1236

Max Act: 1.5345. Min Act: -0.0000

Data Index: 1293274 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 3.1236. Min Range: -3.1236

Max Act: 1.4444. Min Act: -0.0000

Data Index: 571308 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 3.1236. Min Range: -3.1236

Max Act: 1.4922. Min Act: -0.0000

Data Index: 787362 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 3.1236. Min Range: -3.1236

Max Act: 1.2319. Min Act: -0.0000

Data Index: 650905 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 3.1236. Min Range: -3.1236

Max Act: 1.3407. Min Act: -0.0000

Data Index: 931206 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 3.1236. Min Range: -3.1236

Max Act: 1.2521. Min Act: -0.0000

Data Index: 1162491 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 3.1236. Min Range: -3.1236

Max Act: 1.3154. Min Act: -0.0000

Data Index: 1343829 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 3.1236. Min Range: -3.1236

Max Act: 1.3116. Min Act: -0.0000

Data Index: 581344 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 3.1236. Min Range: -3.1236

Max Act: 1.2353. Min Act: -0.0000

Data Index: 233423 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 3.1236. Min Range: -3.1236

Max Act: 1.1529. Min Act: -0.0000

Data Index: 1200603 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 3.1236. Min Range: -3.1236

Max Act: 1.1779. Min Act: -0.0000

Data Index: 1193782 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 3.1236. Min Range: -3.1236

Max Act: 1.1092. Min Act: -0.0000

Data Index: 58037 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 3.1236. Min Range: -3.1236

Max Act: 1.3145. Min Act: -0.0000

Data Index: 1012093 (C4 (Web Text))

Max Activating Token Index: 688