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

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

Neuron 2732 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.6255. Min Act: -0.0001

Data Index: 1471622 (Python Code)

Max Activating Token Index: 339

Text #1

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1627830 (Python Code)

Max Activating Token Index: 622

Text #2

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.6032. Min Act: -0.0001

Data Index: 1400708 (Python Code)

Max Activating Token Index: 531

Text #3

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5601. Min Act: -0.0001

Data Index: 1423090 (Python Code)

Max Activating Token Index: 73

Text #4

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5337. Min Act: -0.0001

Data Index: 1450583 (Python Code)

Max Activating Token Index: 240

Text #5

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5538. Min Act: -0.0001

Data Index: 1551292 (Python Code)

Max Activating Token Index: 632

Text #6

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5034. Min Act: -0.0001

Data Index: 1413077 (Python Code)

Max Activating Token Index: 1013

Text #7

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4987. Min Act: -0.0001

Data Index: 1444656 (Python Code)

Max Activating Token Index: 210

Text #8

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5085. Min Act: -0.0001

Data Index: 1508740 (Python Code)

Max Activating Token Index: 907

Text #9

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4309. Min Act: -0.0001

Data Index: 1653937 (Python Code)

Max Activating Token Index: 729

Text #10

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4597. Min Act: -0.0001

Data Index: 1483345 (Python Code)

Max Activating Token Index: 602

Text #11

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4858. Min Act: -0.0001

Data Index: 1512335 (Python Code)

Max Activating Token Index: 167

Text #12

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1441701 (Python Code)

Max Activating Token Index: 699

Text #13

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4705. Min Act: -0.0001

Data Index: 1419881 (Python Code)

Max Activating Token Index: 406

Text #14

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4504. Min Act: -0.0001

Data Index: 1589981 (Python Code)

Max Activating Token Index: 942

Text #15

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4188. Min Act: -0.0001

Data Index: 1499218 (Python Code)

Max Activating Token Index: 799

Text #16

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4388. Min Act: -0.0001

Data Index: 1470853 (Python Code)

Max Activating Token Index: 786

Text #17

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4645. Min Act: -0.0001

Data Index: 1613979 (Python Code)

Max Activating Token Index: 898

Text #18

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4816. Min Act: -0.0000

Data Index: 1456515 (Python Code)

Max Activating Token Index: 518

Text #19

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4303. Min Act: -0.0001

Data Index: 1443380 (Python Code)

Max Activating Token Index: 245