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

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

Neuron 473 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: 2.1185. Min Range: -2.1185

Max Act: 2.1185. Min Act: -0.0000

Data Index: 1016386 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 2.1185. Min Range: -2.1185

Max Act: 1.8668. Min Act: -0.0000

Data Index: 1332925 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 2.1185. Min Range: -2.1185

Max Act: 1.9350. Min Act: -0.0000

Data Index: 443271 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 2.1185. Min Range: -2.1185

Max Act: 2.0080. Min Act: -0.0000

Data Index: 367170 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 2.1185. Min Range: -2.1185

Max Act: 1.7828. Min Act: -0.0000

Data Index: 848405 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 2.1185. Min Range: -2.1185

Max Act: 1.9683. Min Act: -0.0000

Data Index: 1349478 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 2.1185. Min Range: -2.1185

Max Act: 1.9526. Min Act: -0.0000

Data Index: 867415 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 2.1185. Min Range: -2.1185

Max Act: 1.7960. Min Act: -0.0000

Data Index: 467284 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 2.1185. Min Range: -2.1185

Max Act: 1.7682. Min Act: -0.0000

Data Index: 1063039 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 2.1185. Min Range: -2.1185

Max Act: 1.8554. Min Act: -0.0000

Data Index: 672490 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 2.1185. Min Range: -2.1185

Max Act: 1.7347. Min Act: -0.0000

Data Index: 1350651 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 2.1185. Min Range: -2.1185

Max Act: 1.7513. Min Act: -0.0000

Data Index: 736996 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 2.1185. Min Range: -2.1185

Max Act: 1.6383. Min Act: -0.0000

Data Index: 1539603 (Python Code)

Max Activating Token Index: 22

Text #13

Max Range: 2.1185. Min Range: -2.1185

Max Act: 1.7286. Min Act: -0.0000

Data Index: 947747 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 2.1185. Min Range: -2.1185

Max Act: 1.6269. Min Act: -0.0000

Data Index: 1201908 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 2.1185. Min Range: -2.1185

Max Act: 1.6076. Min Act: -0.0000

Data Index: 1343656 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 2.1185. Min Range: -2.1185

Max Act: 1.6114. Min Act: -0.0000

Data Index: 1272597 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 2.1185. Min Range: -2.1185

Max Act: 1.6882. Min Act: -0.0000

Data Index: 1407886 (Python Code)

Max Activating Token Index: 69

Text #18

Max Range: 2.1185. Min Range: -2.1185

Max Act: 1.5858. Min Act: -0.0000

Data Index: 1412334 (Python Code)

Max Activating Token Index: 8

Text #19

Max Range: 2.1185. Min Range: -2.1185

Max Act: 1.5679. Min Act: -0.0000

Data Index: 1493028 (Python Code)

Max Activating Token Index: 435