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

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

Neuron 85 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: 0.6280. Min Range: -0.6280

Max Act: 0.6238. Min Act: -0.0001

Data Index: 1257821 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.6238. Min Act: -0.0001

Data Index: 766702 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.6238. Min Act: -0.0001

Data Index: 289950 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.6238. Min Act: -0.0001

Data Index: 742636 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.6215. Min Act: -0.0001

Data Index: 855393 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.6019. Min Act: -0.0001

Data Index: 1064738 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.6019. Min Act: -0.0001

Data Index: 863621 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.6019. Min Act: -0.0001

Data Index: 421074 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.6103. Min Act: -0.0001

Data Index: 1359210 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.6090. Min Act: -0.0001

Data Index: 123655 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.6280. Min Act: -0.0001

Data Index: 885784 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.6023. Min Act: -0.0001

Data Index: 1133282 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.5888. Min Act: -0.0001

Data Index: 410338 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.5798. Min Act: -0.0001

Data Index: 504677 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.5798. Min Act: -0.0001

Data Index: 1152987 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.5798. Min Act: -0.0001

Data Index: 52379 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.5685. Min Act: -0.0001

Data Index: 1188614 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.5663. Min Act: -0.0001

Data Index: 75325 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.5820. Min Act: -0.0001

Data Index: 1061984 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.5553. Min Act: -0.0001

Data Index: 939977 (C4 (Web Text))

Max Activating Token Index: 11