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

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

Neuron 536 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.3124. Min Act: -0.0000

Data Index: 464865 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2865. Min Act: -0.0001

Data Index: 388847 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2798. Min Act: -0.0001

Data Index: 1267594 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2777. Min Act: -0.0000

Data Index: 683040 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2547. Min Act: -0.0000

Data Index: 397447 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2445. Min Act: -0.0000

Data Index: 437137 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2524. Min Act: -0.0000

Data Index: 1355226 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2483. Min Act: -0.0001

Data Index: 624916 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2461. Min Act: -0.0000

Data Index: 225049 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2447. Min Act: -0.0000

Data Index: 1120296 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2614. Min Act: -0.0001

Data Index: 914081 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2165. Min Act: -0.0001

Data Index: 526210 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2476. Min Act: -0.0000

Data Index: 1006028 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2404. Min Act: -0.0000

Data Index: 558049 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2531. Min Act: -0.0000

Data Index: 220056 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2279. Min Act: -0.0000

Data Index: 560394 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2441. Min Act: -0.0001

Data Index: 293112 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2248. Min Act: -0.0000

Data Index: 1165762 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2241. Min Act: -0.0000

Data Index: 650432 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2155. Min Act: -0.0000

Data Index: 1099013 (C4 (Web Text))

Max Activating Token Index: 797