Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1360 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.3311. Min Act: -0.0003

Data Index: 1589226 (Python Code)

Max Activating Token Index: 468

Text #1

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2927. Min Act: -0.0003

Data Index: 1608104 (Python Code)

Max Activating Token Index: 144

Text #2

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2956. Min Act: -0.0003

Data Index: 1400784 (Python Code)

Max Activating Token Index: 425

Text #3

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2801. Min Act: -0.0003

Data Index: 1530265 (Python Code)

Max Activating Token Index: 791

Text #4

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2702. Min Act: -0.0003

Data Index: 1368912 (Python Code)

Max Activating Token Index: 44

Text #5

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2526. Min Act: -0.0003

Data Index: 1396147 (Python Code)

Max Activating Token Index: 723

Text #6

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2467. Min Act: -0.0003

Data Index: 1535986 (Python Code)

Max Activating Token Index: 614

Text #7

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2466. Min Act: -0.0003

Data Index: 1450079 (Python Code)

Max Activating Token Index: 570

Text #8

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2455. Min Act: -0.0003

Data Index: 1528053 (Python Code)

Max Activating Token Index: 41

Text #9

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2509. Min Act: -0.0003

Data Index: 1556133 (Python Code)

Max Activating Token Index: 274

Text #10

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2406. Min Act: -0.0003

Data Index: 1579834 (Python Code)

Max Activating Token Index: 37

Text #11

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2400. Min Act: -0.0003

Data Index: 1483954 (Python Code)

Max Activating Token Index: 413

Text #12

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2222. Min Act: -0.0003

Data Index: 1567271 (Python Code)

Max Activating Token Index: 1009

Text #13

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2471. Min Act: -0.0003

Data Index: 1543417 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2466. Min Act: -0.0003

Data Index: 1368902 (Python Code)

Max Activating Token Index: 162

Text #15

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2368. Min Act: -0.0003

Data Index: 1429930 (Python Code)

Max Activating Token Index: 23

Text #16

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2366. Min Act: -0.0003

Data Index: 1374199 (Python Code)

Max Activating Token Index: 144

Text #17

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2528. Min Act: -0.0003

Data Index: 1475042 (Python Code)

Max Activating Token Index: 90

Text #18

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2444. Min Act: -0.0003

Data Index: 1555628 (Python Code)

Max Activating Token Index: 42

Text #19

Max Range: 0.3311. Min Range: -0.3311

Max Act: 0.2178. Min Act: -0.0003

Data Index: 1493850 (Python Code)

Max Activating Token Index: 610