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

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

Neuron 707 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: 2.0925. Min Range: -2.0925

Max Act: 2.0925. Min Act: -0.0000

Data Index: 250393 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.9051. Min Act: -0.0000

Data Index: 1058489 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.9653. Min Act: -0.0001

Data Index: 774566 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.8438. Min Act: -0.0001

Data Index: 2127 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.9224. Min Act: -0.0001

Data Index: 1040984 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.8197. Min Act: -0.0001

Data Index: 660942 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.8609. Min Act: -0.0000

Data Index: 459176 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.7326. Min Act: -0.0001

Data Index: 984412 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.6237. Min Act: -0.0000

Data Index: 1344950 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.6695. Min Act: -0.0000

Data Index: 605577 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.6262. Min Act: -0.0000

Data Index: 258100 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.5084. Min Act: -0.0001

Data Index: 895200 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.5848. Min Act: -0.0000

Data Index: 305834 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.5380. Min Act: -0.0000

Data Index: 672688 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.5771. Min Act: -0.0001

Data Index: 663759 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.5694. Min Act: -0.0000

Data Index: 688950 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.5722. Min Act: -0.0001

Data Index: 1281074 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.5964. Min Act: -0.0000

Data Index: 1106805 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.5187. Min Act: -0.0001

Data Index: 1267144 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.5069. Min Act: -0.0000

Data Index: 671019 (C4 (Web Text))

Max Activating Token Index: 325