Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4381 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0561. Min Act: -0.0002

Data Index: 530733 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1158014 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0514. Min Act: -0.0002

Data Index: 963708 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0525. Min Act: -0.0002

Data Index: 620435 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0525. Min Act: -0.0002

Data Index: 910971 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0485. Min Act: -0.0002

Data Index: 846492 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1056367 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0495. Min Act: -0.0002

Data Index: 546320 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1302768 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0549. Min Act: -0.0002

Data Index: 991523 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1301601 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0450. Min Act: -0.0002

Data Index: 4639 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1329878 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0482. Min Act: -0.0002

Data Index: 86569 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0452. Min Act: -0.0002

Data Index: 879583 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0466. Min Act: -0.0002

Data Index: 558415 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0421. Min Act: -0.0002

Data Index: 217806 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1222845 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0450. Min Act: -0.0002

Data Index: 551430 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0442. Min Act: -0.0002

Data Index: 346255 (C4 (Web Text))

Max Activating Token Index: 881