Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 417 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0549. Min Act: -0.0002

Data Index: 162081 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0547. Min Act: -0.0002

Data Index: 636738 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0552. Min Act: -0.0002

Data Index: 600877 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0510. Min Act: -0.0002

Data Index: 1358679 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0488. Min Act: -0.0002

Data Index: 245436 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0457. Min Act: -0.0002

Data Index: 346932 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0452. Min Act: -0.0002

Data Index: 289122 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1194211 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0427. Min Act: -0.0002

Data Index: 102553 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0441. Min Act: -0.0002

Data Index: 462877 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0442. Min Act: -0.0002

Data Index: 835466 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1137060 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0438. Min Act: -0.0002

Data Index: 27785 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0438. Min Act: -0.0002

Data Index: 892338 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0421. Min Act: -0.0002

Data Index: 699258 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1197343 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0407. Min Act: -0.0002

Data Index: 465100 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0398. Min Act: -0.0002

Data Index: 619179 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0413. Min Act: -0.0002

Data Index: 118690 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1174365 (C4 (Web Text))

Max Activating Token Index: 132