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

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

Neuron 789 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.4419. Min Act: -0.0001

Data Index: 1563945 (Python Code)

Max Activating Token Index: 968

Text #1

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.3991. Min Act: -0.0000

Data Index: 1558346 (Python Code)

Max Activating Token Index: 226

Text #2

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.4285. Min Act: -0.0001

Data Index: 1459682 (Python Code)

Max Activating Token Index: 156

Text #3

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1538506 (Python Code)

Max Activating Token Index: 196

Text #4

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.4035. Min Act: -0.0000

Data Index: 1360848 (Python Code)

Max Activating Token Index: 88

Text #5

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.4027. Min Act: -0.0001

Data Index: 1608258 (Python Code)

Max Activating Token Index: 737

Text #6

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.3834. Min Act: -0.0001

Data Index: 1551781 (Python Code)

Max Activating Token Index: 555

Text #7

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.3858. Min Act: -0.0000

Data Index: 110560 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.3510. Min Act: -0.0001

Data Index: 1503604 (Python Code)

Max Activating Token Index: 383

Text #9

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.3420. Min Act: -0.0001

Data Index: 1487854 (Python Code)

Max Activating Token Index: 446

Text #10

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.3266. Min Act: -0.0001

Data Index: 1547051 (Python Code)

Max Activating Token Index: 23

Text #11

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.3123. Min Act: -0.0001

Data Index: 1462692 (Python Code)

Max Activating Token Index: 33

Text #12

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.3116. Min Act: -0.0001

Data Index: 1361223 (Python Code)

Max Activating Token Index: 442

Text #13

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.3006. Min Act: -0.0001

Data Index: 1371002 (Python Code)

Max Activating Token Index: 419

Text #14

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.3179. Min Act: -0.0001

Data Index: 1605963 (Python Code)

Max Activating Token Index: 26

Text #15

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.2946. Min Act: -0.0001

Data Index: 1610706 (Python Code)

Max Activating Token Index: 18

Text #16

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.2858. Min Act: -0.0001

Data Index: 1370802 (Python Code)

Max Activating Token Index: 37

Text #17

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.2949. Min Act: -0.0001

Data Index: 1534995 (Python Code)

Max Activating Token Index: 375

Text #18

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.2820. Min Act: -0.0000

Data Index: 1202202 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 0.4419. Min Range: -0.4419

Max Act: 0.2651. Min Act: -0.0001

Data Index: 1450846 (Python Code)

Max Activating Token Index: 633