Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1450 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0589. Min Act: -0.0003

Data Index: 155451 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0543. Min Act: -0.0004

Data Index: 260376 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0519. Min Act: -0.0003

Data Index: 978408 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0481. Min Act: -0.0003

Data Index: 753270 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0487. Min Act: -0.0003

Data Index: 464696 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1087243 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0470. Min Act: -0.0003

Data Index: 712076 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1266045 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0454. Min Act: -0.0003

Data Index: 248 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0485. Min Act: -0.0003

Data Index: 490248 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0485. Min Act: -0.0003

Data Index: 1127030 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0463. Min Act: -0.0004

Data Index: 959978 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0455. Min Act: -0.0003

Data Index: 538693 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0461. Min Act: -0.0003

Data Index: 441423 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0456. Min Act: -0.0003

Data Index: 1220141 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0460. Min Act: -0.0003

Data Index: 579944 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0444. Min Act: -0.0003

Data Index: 792401 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0450. Min Act: -0.0001

Data Index: 919278 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0452. Min Act: -0.0003

Data Index: 908079 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0451. Min Act: -0.0004

Data Index: 1201873 (C4 (Web Text))

Max Activating Token Index: 184