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

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

Neuron 2231 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4921. Min Range: -1.4921

Max Act: 1.4921. Min Act: -0.0001

Data Index: 1173382 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 1.4921. Min Range: -1.4921

Max Act: 1.1613. Min Act: -0.0001

Data Index: 1606110 (Python Code)

Max Activating Token Index: 532

Text #2

Max Range: 1.4921. Min Range: -1.4921

Max Act: 1.1573. Min Act: -0.0001

Data Index: 1655348 (Python Code)

Max Activating Token Index: 347

Text #3

Max Range: 1.4921. Min Range: -1.4921

Max Act: 1.0633. Min Act: -0.0001

Data Index: 1571094 (Python Code)

Max Activating Token Index: 582

Text #4

Max Range: 1.4921. Min Range: -1.4921

Max Act: 1.1581. Min Act: -0.0001

Data Index: 1456027 (Python Code)

Max Activating Token Index: 775

Text #5

Max Range: 1.4921. Min Range: -1.4921

Max Act: 1.1082. Min Act: -0.0001

Data Index: 1478233 (Python Code)

Max Activating Token Index: 361

Text #6

Max Range: 1.4921. Min Range: -1.4921

Max Act: 1.0030. Min Act: -0.0001

Data Index: 1633658 (Python Code)

Max Activating Token Index: 507

Text #7

Max Range: 1.4921. Min Range: -1.4921

Max Act: 1.0172. Min Act: -0.0001

Data Index: 1588827 (Python Code)

Max Activating Token Index: 19

Text #8

Max Range: 1.4921. Min Range: -1.4921

Max Act: 1.0167. Min Act: -0.0001

Data Index: 1543727 (Python Code)

Max Activating Token Index: 989

Text #9

Max Range: 1.4921. Min Range: -1.4921

Max Act: 0.9808. Min Act: -0.0001

Data Index: 1413811 (Python Code)

Max Activating Token Index: 705

Text #10

Max Range: 1.4921. Min Range: -1.4921

Max Act: 0.9495. Min Act: -0.0001

Data Index: 1572943 (Python Code)

Max Activating Token Index: 247

Text #11

Max Range: 1.4921. Min Range: -1.4921

Max Act: 0.9678. Min Act: -0.0001

Data Index: 1519024 (Python Code)

Max Activating Token Index: 440

Text #12

Max Range: 1.4921. Min Range: -1.4921

Max Act: 0.8509. Min Act: -0.0001

Data Index: 1637340 (Python Code)

Max Activating Token Index: 850

Text #13

Max Range: 1.4921. Min Range: -1.4921

Max Act: 1.0259. Min Act: -0.0001

Data Index: 1425595 (Python Code)

Max Activating Token Index: 868

Text #14

Max Range: 1.4921. Min Range: -1.4921

Max Act: 0.9646. Min Act: -0.0001

Data Index: 1536279 (Python Code)

Max Activating Token Index: 352

Text #15

Max Range: 1.4921. Min Range: -1.4921

Max Act: 0.9286. Min Act: -0.0001

Data Index: 1605161 (Python Code)

Max Activating Token Index: 424

Text #16

Max Range: 1.4921. Min Range: -1.4921

Max Act: 0.8953. Min Act: -0.0001

Data Index: 1549566 (Python Code)

Max Activating Token Index: 252

Text #17

Max Range: 1.4921. Min Range: -1.4921

Max Act: 0.8978. Min Act: -0.0001

Data Index: 1615600 (Python Code)

Max Activating Token Index: 724

Text #18

Max Range: 1.4921. Min Range: -1.4921

Max Act: 0.8958. Min Act: -0.0001

Data Index: 1491546 (Python Code)

Max Activating Token Index: 640

Text #19

Max Range: 1.4921. Min Range: -1.4921

Max Act: 0.9232. Min Act: -0.0001

Data Index: 1416742 (Python Code)

Max Activating Token Index: 58