Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 862 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0501. Min Act: -0.0002

Data Index: 580096 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0496. Min Act: -0.0002

Data Index: 446505 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1018681 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0476. Min Act: -0.0002

Data Index: 185045 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0485. Min Act: -0.0001

Data Index: 311545 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0465. Min Act: -0.0002

Data Index: 867264 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0436. Min Act: -0.0001

Data Index: 716776 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0464. Min Act: -0.0002

Data Index: 613089 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0455. Min Act: -0.0002

Data Index: 96397 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0450. Min Act: -0.0002

Data Index: 735849 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0456. Min Act: -0.0002

Data Index: 895498 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1165503 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0438. Min Act: -0.0002

Data Index: 519663 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1232309 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0459. Min Act: -0.0002

Data Index: 906141 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0443. Min Act: -0.0002

Data Index: 366396 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0460. Min Act: -0.0002

Data Index: 587212 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0438. Min Act: -0.0002

Data Index: 221284 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0454. Min Act: -0.0002

Data Index: 667329 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0422. Min Act: -0.0001

Data Index: 279924 (C4 (Web Text))

Max Activating Token Index: 442