Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3698 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.4169. Min Act: -0.0001

Data Index: 1432667 (Python Code)

Max Activating Token Index: 92

Text #1

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.4176. Min Act: -0.0001

Data Index: 1361134 (Python Code)

Max Activating Token Index: 644

Text #2

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3403. Min Act: -0.0001

Data Index: 1474222 (Python Code)

Max Activating Token Index: 284

Text #3

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3615. Min Act: -0.0001

Data Index: 1372791 (Python Code)

Max Activating Token Index: 246

Text #4

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3260. Min Act: -0.0000

Data Index: 1544226 (Python Code)

Max Activating Token Index: 342

Text #5

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3270. Min Act: -0.0001

Data Index: 1371848 (Python Code)

Max Activating Token Index: 939

Text #6

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3074. Min Act: -0.0001

Data Index: 1469354 (Python Code)

Max Activating Token Index: 617

Text #7

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3137. Min Act: -0.0001

Data Index: 1456402 (Python Code)

Max Activating Token Index: 354

Text #8

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.3039. Min Act: -0.0001

Data Index: 1580559 (Python Code)

Max Activating Token Index: 348

Text #9

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2914. Min Act: -0.0001

Data Index: 1632613 (Python Code)

Max Activating Token Index: 708

Text #10

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2856. Min Act: -0.0001

Data Index: 1586398 (Python Code)

Max Activating Token Index: 416

Text #11

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2594. Min Act: -0.0001

Data Index: 1481190 (Python Code)

Max Activating Token Index: 284

Text #12

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2925. Min Act: -0.0001

Data Index: 1397820 (Python Code)

Max Activating Token Index: 817

Text #13

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2623. Min Act: -0.0001

Data Index: 1576563 (Python Code)

Max Activating Token Index: 360

Text #14

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2741. Min Act: -0.0001

Data Index: 1396475 (Python Code)

Max Activating Token Index: 789

Text #15

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2660. Min Act: -0.0001

Data Index: 1486164 (Python Code)

Max Activating Token Index: 333

Text #16

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2667. Min Act: -0.0001

Data Index: 1588619 (Python Code)

Max Activating Token Index: 80

Text #17

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2547. Min Act: -0.0001

Data Index: 1586683 (Python Code)

Max Activating Token Index: 507

Text #18

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2464. Min Act: -0.0001

Data Index: 1449650 (Python Code)

Max Activating Token Index: 990

Text #19

Max Range: 0.4176. Min Range: -0.4176

Max Act: 0.2460. Min Act: -0.0001

Data Index: 1388278 (Python Code)

Max Activating Token Index: 881