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

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

Neuron 4230 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6601. Min Range: -4.6601

Max Act: 4.6601. Min Act: -0.0000

Data Index: 1087551 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 4.6601. Min Range: -4.6601

Max Act: 0.0460. Min Act: -0.0000

Data Index: 370143 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 4.6601. Min Range: -4.6601

Max Act: 0.0522. Min Act: -0.0000

Data Index: 542707 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 4.6601. Min Range: -4.6601

Max Act: 0.0577. Min Act: -0.0000

Data Index: 239485 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 4.6601. Min Range: -4.6601

Max Act: 0.0488. Min Act: -0.0000

Data Index: 705080 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 4.6601. Min Range: -4.6601

Max Act: 0.0415. Min Act: -0.0000

Data Index: 1175653 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 4.6601. Min Range: -4.6601

Max Act: 0.0415. Min Act: -0.0000

Data Index: 1081031 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 4.6601. Min Range: -4.6601

Max Act: 0.0457. Min Act: -0.0000

Data Index: 1250136 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 4.6601. Min Range: -4.6601

Max Act: 0.0475. Min Act: -0.0000

Data Index: 24653 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 4.6601. Min Range: -4.6601

Max Act: 0.0442. Min Act: -0.0000

Data Index: 219248 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 4.6601. Min Range: -4.6601

Max Act: 0.0412. Min Act: -0.0000

Data Index: 503050 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 4.6601. Min Range: -4.6601

Max Act: 0.0405. Min Act: -0.0000

Data Index: 1635737 (Python Code)

Max Activating Token Index: 949

Text #12

Max Range: 4.6601. Min Range: -4.6601

Max Act: 0.0414. Min Act: -0.0000

Data Index: 1562740 (Python Code)

Max Activating Token Index: 185

Text #13

Max Range: 4.6601. Min Range: -4.6601

Max Act: 0.0397. Min Act: -0.0000

Data Index: 720763 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 4.6601. Min Range: -4.6601

Max Act: 0.0380. Min Act: -0.0000

Data Index: 1507362 (Python Code)

Max Activating Token Index: 962

Text #15

Max Range: 4.6601. Min Range: -4.6601

Max Act: 0.0417. Min Act: -0.0000

Data Index: 996076 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 4.6601. Min Range: -4.6601

Max Act: 0.0390. Min Act: -0.0000

Data Index: 429150 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 4.6601. Min Range: -4.6601

Max Act: 0.0373. Min Act: -0.0000

Data Index: 985209 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 4.6601. Min Range: -4.6601

Max Act: 0.0400. Min Act: -0.0000

Data Index: 781013 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 4.6601. Min Range: -4.6601

Max Act: 0.0397. Min Act: -0.0000

Data Index: 1642013 (Python Code)

Max Activating Token Index: 792