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

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

Neuron 1254 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: 0.0597. Min Range: -0.0597

Max Act: 0.0597. Min Act: -0.0002

Data Index: 383260 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0576. Min Act: -0.0002

Data Index: 894385 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0562. Min Act: -0.0002

Data Index: 253888 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0580. Min Act: -0.0001

Data Index: 399176 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0562. Min Act: -0.0002

Data Index: 374132 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0554. Min Act: -0.0002

Data Index: 385001 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0553. Min Act: -0.0002

Data Index: 362674 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0557. Min Act: -0.0002

Data Index: 807585 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1339188 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0545. Min Act: -0.0002

Data Index: 999604 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0540. Min Act: -0.0002

Data Index: 954698 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0539. Min Act: -0.0002

Data Index: 575592 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1191550 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0546. Min Act: -0.0002

Data Index: 406147 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1109666 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0534. Min Act: -0.0002

Data Index: 223495 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0521. Min Act: -0.0002

Data Index: 52623 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0540. Min Act: -0.0001

Data Index: 956471 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0522. Min Act: -0.0002

Data Index: 805113 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0538. Min Act: -0.0002

Data Index: 813457 (C4 (Web Text))

Max Activating Token Index: 761