Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3621 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9711. Min Range: -0.9711

Max Act: 0.9711. Min Act: -0.0000

Data Index: 516519 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.9711. Min Range: -0.9711

Max Act: 0.9260. Min Act: -0.0000

Data Index: 1348548 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.9711. Min Range: -0.9711

Max Act: 0.8747. Min Act: -0.0000

Data Index: 183004 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.9711. Min Range: -0.9711

Max Act: 0.8165. Min Act: -0.0000

Data Index: 1403503 (Python Code)

Max Activating Token Index: 128

Text #4

Max Range: 0.9711. Min Range: -0.9711

Max Act: 0.7882. Min Act: -0.0000

Data Index: 553983 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.9711. Min Range: -0.9711

Max Act: 0.7933. Min Act: -0.0000

Data Index: 1595179 (Python Code)

Max Activating Token Index: 389

Text #6

Max Range: 0.9711. Min Range: -0.9711

Max Act: 0.7705. Min Act: -0.0000

Data Index: 646912 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 0.9711. Min Range: -0.9711

Max Act: 0.7917. Min Act: -0.0000

Data Index: 1126844 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.9711. Min Range: -0.9711

Max Act: 0.7474. Min Act: -0.0000

Data Index: 936043 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 0.9711. Min Range: -0.9711

Max Act: 0.7229. Min Act: -0.0000

Data Index: 413187 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.9711. Min Range: -0.9711

Max Act: 0.7405. Min Act: -0.0000

Data Index: 849930 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.9711. Min Range: -0.9711

Max Act: 0.7097. Min Act: -0.0000

Data Index: 1510556 (Python Code)

Max Activating Token Index: 183

Text #12

Max Range: 0.9711. Min Range: -0.9711

Max Act: 0.7472. Min Act: -0.0000

Data Index: 534911 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.9711. Min Range: -0.9711

Max Act: 0.7395. Min Act: -0.0000

Data Index: 502531 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.9711. Min Range: -0.9711

Max Act: 0.7118. Min Act: -0.0000

Data Index: 544260 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.9711. Min Range: -0.9711

Max Act: 0.7069. Min Act: -0.0000

Data Index: 901298 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.9711. Min Range: -0.9711

Max Act: 0.7066. Min Act: -0.0000

Data Index: 867425 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.9711. Min Range: -0.9711

Max Act: 0.7301. Min Act: -0.0000

Data Index: 184552 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 0.9711. Min Range: -0.9711

Max Act: 0.7011. Min Act: -0.0000

Data Index: 1300867 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.9711. Min Range: -0.9711

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1367374 (Python Code)

Max Activating Token Index: 299