Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 466 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0528. Min Act: -0.0006

Data Index: 1298650 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0531. Min Act: -0.0006

Data Index: 763574 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0480. Min Act: -0.0006

Data Index: 1216888 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0522. Min Act: -0.0006

Data Index: 813543 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0484. Min Act: -0.0006

Data Index: 1244615 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0533. Min Act: -0.0006

Data Index: 1068544 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0503. Min Act: -0.0006

Data Index: 834143 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0419. Min Act: -0.0006

Data Index: 665466 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0454. Min Act: -0.0006

Data Index: 103581 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0430. Min Act: -0.0006

Data Index: 1025624 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0490. Min Act: -0.0006

Data Index: 693941 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0489. Min Act: -0.0006

Data Index: 588941 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0417. Min Act: -0.0006

Data Index: 287391 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0404. Min Act: -0.0006

Data Index: 450205 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0416. Min Act: -0.0006

Data Index: 1054744 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0417. Min Act: -0.0006

Data Index: 1216284 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0431. Min Act: -0.0006

Data Index: 1339173 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0393. Min Act: -0.0006

Data Index: 891547 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0407. Min Act: -0.0006

Data Index: 1101284 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0382. Min Act: -0.0006

Data Index: 897980 (C4 (Web Text))

Max Activating Token Index: 153