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

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

Neuron 2695 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: 0.0520. Min Range: -0.0520

Max Act: 0.0520. Min Act: -0.0002

Data Index: 524205 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0482. Min Act: -0.0002

Data Index: 48501 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1280552 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1291231 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0471. Min Act: -0.0002

Data Index: 715061 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0450. Min Act: -0.0002

Data Index: 970532 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1331143 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0429. Min Act: -0.0002

Data Index: 176588 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0449. Min Act: -0.0002

Data Index: 429351 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0445. Min Act: -0.0002

Data Index: 240729 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0426. Min Act: -0.0002

Data Index: 414008 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0455. Min Act: -0.0002

Data Index: 681324 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1315157 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0437. Min Act: -0.0002

Data Index: 991981 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0446. Min Act: -0.0002

Data Index: 876328 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0424. Min Act: -0.0002

Data Index: 645010 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0418. Min Act: -0.0002

Data Index: 766560 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0423. Min Act: -0.0002

Data Index: 934385 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1131261 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0416. Min Act: -0.0002

Data Index: 116266 (C4 (Web Text))

Max Activating Token Index: 468