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

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

Neuron 5015 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4326. Min Range: -2.4326

Max Act: 2.3371. Min Act: -0.0000

Data Index: 973825 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 2.4326. Min Range: -2.4326

Max Act: 2.2429. Min Act: -0.0000

Data Index: 1252607 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 2.4326. Min Range: -2.4326

Max Act: 2.1077. Min Act: -0.0000

Data Index: 741899 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 2.4326. Min Range: -2.4326

Max Act: 2.2342. Min Act: -0.0000

Data Index: 980609 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 2.4326. Min Range: -2.4326

Max Act: 2.1979. Min Act: -0.0000

Data Index: 495089 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 2.4326. Min Range: -2.4326

Max Act: 2.3262. Min Act: -0.0000

Data Index: 1212281 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 2.4326. Min Range: -2.4326

Max Act: 2.2089. Min Act: -0.0000

Data Index: 1213399 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 2.4326. Min Range: -2.4326

Max Act: 2.2082. Min Act: -0.0001

Data Index: 1003495 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 2.4326. Min Range: -2.4326

Max Act: 2.2172. Min Act: -0.0000

Data Index: 767475 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 2.4326. Min Range: -2.4326

Max Act: 2.2130. Min Act: -0.0000

Data Index: 165939 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 2.4326. Min Range: -2.4326

Max Act: 2.4322. Min Act: -0.0000

Data Index: 53467 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 2.4326. Min Range: -2.4326

Max Act: 2.3107. Min Act: -0.0000

Data Index: 1057232 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 2.4326. Min Range: -2.4326

Max Act: 2.4326. Min Act: -0.0001

Data Index: 84900 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 2.4326. Min Range: -2.4326

Max Act: 2.3052. Min Act: -0.0000

Data Index: 115379 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 2.4326. Min Range: -2.4326

Max Act: 2.3182. Min Act: -0.0001

Data Index: 525785 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 2.4326. Min Range: -2.4326

Max Act: 2.1380. Min Act: -0.0001

Data Index: 972584 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 2.4326. Min Range: -2.4326

Max Act: 2.2333. Min Act: -0.0001

Data Index: 411597 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 2.4326. Min Range: -2.4326

Max Act: 2.2240. Min Act: -0.0000

Data Index: 1048036 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 2.4326. Min Range: -2.4326

Max Act: 2.3439. Min Act: -0.0001

Data Index: 51034 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 2.4326. Min Range: -2.4326

Max Act: 2.2157. Min Act: -0.0001

Data Index: 1146754 (C4 (Web Text))

Max Activating Token Index: 773