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

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

Neuron 3988 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: 0.5875. Min Range: -0.5875

Max Act: 0.5875. Min Act: 0.0000

Data Index: 1173484 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5654. Min Act: -0.0000

Data Index: 16148 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5295. Min Act: -0.0000

Data Index: 402464 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4849. Min Act: -0.0000

Data Index: 503070 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4713. Min Act: -0.0000

Data Index: 229102 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4736. Min Act: -0.0000

Data Index: 738816 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4983. Min Act: 0.0001

Data Index: 1275435 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4498. Min Act: 0.0001

Data Index: 32840 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4621. Min Act: -0.0001

Data Index: 347861 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4478. Min Act: -0.0000

Data Index: 501819 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4335. Min Act: -0.0000

Data Index: 362129 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4319. Min Act: 0.0001

Data Index: 984096 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4287. Min Act: 0.0001

Data Index: 1253952 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4115. Min Act: -0.0000

Data Index: 1149137 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4068. Min Act: -0.0000

Data Index: 760207 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4144. Min Act: -0.0000

Data Index: 919900 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4090. Min Act: -0.0000

Data Index: 582770 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4059. Min Act: -0.0001

Data Index: 660489 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4168. Min Act: -0.0000

Data Index: 13174 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4099. Min Act: -0.0000

Data Index: 1224479 (C4 (Web Text))

Max Activating Token Index: 564