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

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

Neuron 1588 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0526. Min Act: -0.0005

Data Index: 186484 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0540. Min Act: -0.0005

Data Index: 916348 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0514. Min Act: -0.0005

Data Index: 1135946 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0502. Min Act: -0.0005

Data Index: 400044 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0505. Min Act: -0.0005

Data Index: 447105 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0474. Min Act: -0.0005

Data Index: 1103439 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0484. Min Act: -0.0005

Data Index: 404521 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0450. Min Act: -0.0005

Data Index: 175720 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0475. Min Act: -0.0005

Data Index: 711090 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0467. Min Act: -0.0005

Data Index: 1339400 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0472. Min Act: -0.0005

Data Index: 178288 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0463. Min Act: -0.0005

Data Index: 244186 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0460. Min Act: -0.0005

Data Index: 443529 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0452. Min Act: -0.0005

Data Index: 1111938 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0443. Min Act: -0.0005

Data Index: 587149 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0460. Min Act: -0.0005

Data Index: 714539 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0426. Min Act: -0.0005

Data Index: 766175 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0439. Min Act: -0.0005

Data Index: 77806 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0428. Min Act: -0.0005

Data Index: 304817 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0454. Min Act: -0.0005

Data Index: 584471 (C4 (Web Text))

Max Activating Token Index: 178