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

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

Neuron 2295 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.2101. Min Act: -0.0001

Data Index: 588443 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1904. Min Act: -0.0001

Data Index: 1037705 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1291. Min Act: -0.0001

Data Index: 4696 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1069. Min Act: -0.0001

Data Index: 759 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1524423 (Python Code)

Max Activating Token Index: 196

Text #5

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.0962. Min Act: -0.0001

Data Index: 502042 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.0909. Min Act: -0.0001

Data Index: 1579727 (Python Code)

Max Activating Token Index: 728

Text #7

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1615472 (Python Code)

Max Activating Token Index: 135

Text #8

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1007. Min Act: -0.0001

Data Index: 848451 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.0885. Min Act: -0.0001

Data Index: 1542562 (Python Code)

Max Activating Token Index: 594

Text #10

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.0973. Min Act: -0.0001

Data Index: 528280 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.0867. Min Act: -0.0001

Data Index: 1375223 (Python Code)

Max Activating Token Index: 397

Text #12

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.0715. Min Act: -0.0000

Data Index: 1027787 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.0857. Min Act: -0.0001

Data Index: 294411 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.0918. Min Act: -0.0001

Data Index: 964445 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.0920. Min Act: -0.0001

Data Index: 123426 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.0822. Min Act: -0.0001

Data Index: 49091 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.0859. Min Act: -0.0001

Data Index: 1426941 (Python Code)

Max Activating Token Index: 504

Text #18

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.0835. Min Act: -0.0001

Data Index: 866325 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.0831. Min Act: -0.0001

Data Index: 1487068 (Python Code)

Max Activating Token Index: 855