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

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

Neuron 5759 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1572978 (Python Code)

Max Activating Token Index: 36

Text #1

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.4690. Min Act: -0.0000

Data Index: 80564 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.4728. Min Act: -0.0000

Data Index: 1475416 (Python Code)

Max Activating Token Index: 21

Text #3

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1240163 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1301254 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1572907 (Python Code)

Max Activating Token Index: 268

Text #6

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1606388 (Python Code)

Max Activating Token Index: 284

Text #7

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3907. Min Act: -0.0000

Data Index: 1599315 (Python Code)

Max Activating Token Index: 223

Text #8

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1523149 (Python Code)

Max Activating Token Index: 176

Text #9

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.4019. Min Act: -0.0000

Data Index: 1528401 (Python Code)

Max Activating Token Index: 230

Text #10

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3548. Min Act: -0.0000

Data Index: 1535211 (Python Code)

Max Activating Token Index: 226

Text #11

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.4062. Min Act: -0.0000

Data Index: 1457087 (Python Code)

Max Activating Token Index: 74

Text #12

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.4016. Min Act: -0.0000

Data Index: 242911 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3664. Min Act: -0.0000

Data Index: 1410118 (Python Code)

Max Activating Token Index: 192

Text #14

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1581755 (Python Code)

Max Activating Token Index: 288

Text #15

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3671. Min Act: -0.0000

Data Index: 616522 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1505711 (Python Code)

Max Activating Token Index: 221

Text #17

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1589702 (Python Code)

Max Activating Token Index: 53

Text #18

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1415109 (Python Code)

Max Activating Token Index: 421

Text #19

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1643353 (Python Code)

Max Activating Token Index: 91