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

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

Neuron 4931 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.1998. Min Act: -0.0000

Data Index: 448383 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.3261. Min Act: -0.0000

Data Index: 71406 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.1666. Min Act: -0.0001

Data Index: 8020 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.1252. Min Act: -0.0000

Data Index: 77866 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0453. Min Act: -0.0000

Data Index: 225987 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0602. Min Act: -0.0000

Data Index: 1212253 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0460. Min Act: -0.0000

Data Index: 1060429 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0343. Min Act: -0.0000

Data Index: 921681 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0215. Min Act: -0.0000

Data Index: 582215 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0100. Min Act: -0.0000

Data Index: 377540 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0325. Min Act: -0.0000

Data Index: 696788 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 1.3261. Min Range: -1.3261

Max Act: 0.9982. Min Act: -0.0000

Data Index: 534984 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0875. Min Act: -0.0000

Data Index: 772766 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0000. Min Act: -0.0000

Data Index: 1043807 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 1.3261. Min Range: -1.3261

Max Act: 0.9994. Min Act: -0.0000

Data Index: 23038 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 1.3261. Min Range: -1.3261

Max Act: 0.9774. Min Act: -0.0000

Data Index: 635438 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0544. Min Act: -0.0000

Data Index: 1113023 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 1.3261. Min Range: -1.3261

Max Act: 0.9695. Min Act: -0.0000

Data Index: 433276 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0079. Min Act: -0.0000

Data Index: 381051 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 1.3261. Min Range: -1.3261

Max Act: 1.0310. Min Act: -0.0000

Data Index: 836694 (C4 (Web Text))

Max Activating Token Index: 474