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

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

Neuron 1297 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: 2.3507. Min Range: -2.3507

Max Act: 2.3507. Min Act: -0.0000

Data Index: 1086971 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 2.3507. Min Range: -2.3507

Max Act: 1.7421. Min Act: -0.0000

Data Index: 1246012 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 2.3507. Min Range: -2.3507

Max Act: 1.8277. Min Act: -0.0000

Data Index: 1548404 (Python Code)

Max Activating Token Index: 149

Text #3

Max Range: 2.3507. Min Range: -2.3507

Max Act: 1.6278. Min Act: -0.0000

Data Index: 683818 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 2.3507. Min Range: -2.3507

Max Act: 1.6491. Min Act: -0.0000

Data Index: 1135716 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 2.3507. Min Range: -2.3507

Max Act: 1.4338. Min Act: -0.0000

Data Index: 1152316 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 2.3507. Min Range: -2.3507

Max Act: 1.4301. Min Act: -0.0000

Data Index: 1286025 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 2.3507. Min Range: -2.3507

Max Act: 1.5099. Min Act: -0.0000

Data Index: 340367 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 2.3507. Min Range: -2.3507

Max Act: 1.8049. Min Act: -0.0000

Data Index: 666582 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 2.3507. Min Range: -2.3507

Max Act: 1.4713. Min Act: -0.0000

Data Index: 723615 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 2.3507. Min Range: -2.3507

Max Act: 1.0732. Min Act: -0.0000

Data Index: 311873 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 2.3507. Min Range: -2.3507

Max Act: 1.7422. Min Act: -0.0000

Data Index: 441881 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 2.3507. Min Range: -2.3507

Max Act: 1.5558. Min Act: -0.0000

Data Index: 856412 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 2.3507. Min Range: -2.3507

Max Act: 1.3875. Min Act: -0.0000

Data Index: 1306842 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 2.3507. Min Range: -2.3507

Max Act: 1.6481. Min Act: -0.0000

Data Index: 1221303 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 2.3507. Min Range: -2.3507

Max Act: 1.6291. Min Act: -0.0000

Data Index: 1054494 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 2.3507. Min Range: -2.3507

Max Act: 1.6621. Min Act: -0.0000

Data Index: 69599 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 2.3507. Min Range: -2.3507

Max Act: 1.4869. Min Act: -0.0000

Data Index: 1189273 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 2.3507. Min Range: -2.3507

Max Act: 1.4728. Min Act: -0.0000

Data Index: 429937 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 2.3507. Min Range: -2.3507

Max Act: 1.4652. Min Act: -0.0000

Data Index: 636379 (C4 (Web Text))

Max Activating Token Index: 75