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

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

Neuron 1302 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2468. Min Act: -0.0001

Data Index: 1397934 (Python Code)

Max Activating Token Index: 934

Text #1

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2538. Min Act: -0.0001

Data Index: 1490423 (Python Code)

Max Activating Token Index: 1007

Text #2

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2218. Min Act: -0.0001

Data Index: 1540840 (Python Code)

Max Activating Token Index: 921

Text #3

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2429. Min Act: -0.0001

Data Index: 1365725 (Python Code)

Max Activating Token Index: 1014

Text #4

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2473. Min Act: -0.0001

Data Index: 1495533 (Python Code)

Max Activating Token Index: 896

Text #5

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2365. Min Act: -0.0001

Data Index: 1617342 (Python Code)

Max Activating Token Index: 735

Text #6

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2443. Min Act: -0.0001

Data Index: 1566680 (Python Code)

Max Activating Token Index: 980

Text #7

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2325. Min Act: -0.0001

Data Index: 1537149 (Python Code)

Max Activating Token Index: 896

Text #8

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2267. Min Act: -0.0001

Data Index: 1447826 (Python Code)

Max Activating Token Index: 936

Text #9

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2417. Min Act: -0.0001

Data Index: 1389300 (Python Code)

Max Activating Token Index: 61

Text #10

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2384. Min Act: -0.0001

Data Index: 1446693 (Python Code)

Max Activating Token Index: 185

Text #11

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2341. Min Act: -0.0001

Data Index: 1444983 (Python Code)

Max Activating Token Index: 714

Text #12

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2310. Min Act: -0.0001

Data Index: 1584668 (Python Code)

Max Activating Token Index: 217

Text #13

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2376. Min Act: -0.0001

Data Index: 1580884 (Python Code)

Max Activating Token Index: 729

Text #14

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.1942. Min Act: -0.0001

Data Index: 1563312 (Python Code)

Max Activating Token Index: 820

Text #15

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2158. Min Act: -0.0001

Data Index: 127111 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2450. Min Act: -0.0001

Data Index: 1513881 (Python Code)

Max Activating Token Index: 840

Text #17

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2145. Min Act: -0.0001

Data Index: 1485315 (Python Code)

Max Activating Token Index: 934

Text #18

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2311. Min Act: -0.0001

Data Index: 1469447 (Python Code)

Max Activating Token Index: 819

Text #19

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.1969. Min Act: -0.0001

Data Index: 1435677 (Python Code)

Max Activating Token Index: 658