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

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

Neuron 2618 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5413. Min Range: -2.5413

Max Act: 2.4579. Min Act: -0.0000

Data Index: 331255 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 2.5413. Min Range: -2.5413

Max Act: 2.4424. Min Act: -0.0000

Data Index: 127340 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 2.5413. Min Range: -2.5413

Max Act: 2.0224. Min Act: -0.0000

Data Index: 238765 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 2.5413. Min Range: -2.5413

Max Act: 2.4349. Min Act: -0.0000

Data Index: 659954 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 2.5413. Min Range: -2.5413

Max Act: 2.5413. Min Act: -0.0000

Data Index: 180298 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 2.5413. Min Range: -2.5413

Max Act: 2.3830. Min Act: -0.0000

Data Index: 656152 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 2.5413. Min Range: -2.5413

Max Act: 2.0277. Min Act: -0.0000

Data Index: 702312 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 2.5413. Min Range: -2.5413

Max Act: 2.3406. Min Act: -0.0000

Data Index: 708487 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 2.5413. Min Range: -2.5413

Max Act: 2.1178. Min Act: -0.0000

Data Index: 1280267 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 2.5413. Min Range: -2.5413

Max Act: 2.4301. Min Act: -0.0000

Data Index: 454776 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 2.5413. Min Range: -2.5413

Max Act: 2.4081. Min Act: -0.0000

Data Index: 809266 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 2.5413. Min Range: -2.5413

Max Act: 2.1407. Min Act: -0.0000

Data Index: 1023069 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 2.5413. Min Range: -2.5413

Max Act: 2.4682. Min Act: -0.0000

Data Index: 213078 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 2.5413. Min Range: -2.5413

Max Act: 2.1856. Min Act: -0.0000

Data Index: 529291 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 2.5413. Min Range: -2.5413

Max Act: 2.1703. Min Act: -0.0000

Data Index: 553055 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 2.5413. Min Range: -2.5413

Max Act: 2.0425. Min Act: -0.0000

Data Index: 78298 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 2.5413. Min Range: -2.5413

Max Act: 2.2528. Min Act: -0.0000

Data Index: 1298212 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 2.5413. Min Range: -2.5413

Max Act: 1.9209. Min Act: -0.0000

Data Index: 47947 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 2.5413. Min Range: -2.5413

Max Act: 2.1070. Min Act: -0.0000

Data Index: 1289489 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 2.5413. Min Range: -2.5413

Max Act: 1.7908. Min Act: -0.0000

Data Index: 269556 (C4 (Web Text))

Max Activating Token Index: 442