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

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

Neuron 1089 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 3.2758. Min Range: -3.2758

Max Act: 3.2758. Min Act: -0.0002

Data Index: 1599927 (Python Code)

Max Activating Token Index: 858

Text #1

Max Range: 3.2758. Min Range: -3.2758

Max Act: 3.2517. Min Act: -0.0002

Data Index: 1626184 (Python Code)

Max Activating Token Index: 858

Text #2

Max Range: 3.2758. Min Range: -3.2758

Max Act: 3.1381. Min Act: -0.0002

Data Index: 1588022 (Python Code)

Max Activating Token Index: 884

Text #3

Max Range: 3.2758. Min Range: -3.2758

Max Act: 3.0447. Min Act: -0.0002

Data Index: 1545545 (Python Code)

Max Activating Token Index: 809

Text #4

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.9595. Min Act: -0.0002

Data Index: 1417845 (Python Code)

Max Activating Token Index: 876

Text #5

Max Range: 3.2758. Min Range: -3.2758

Max Act: 3.0020. Min Act: -0.0002

Data Index: 1655950 (Python Code)

Max Activating Token Index: 879

Text #6

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.9718. Min Act: -0.0002

Data Index: 1514221 (Python Code)

Max Activating Token Index: 804

Text #7

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.9489. Min Act: -0.0002

Data Index: 1436082 (Python Code)

Max Activating Token Index: 797

Text #8

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.9607. Min Act: -0.0002

Data Index: 1381499 (Python Code)

Max Activating Token Index: 931

Text #9

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.9876. Min Act: -0.0002

Data Index: 1450974 (Python Code)

Max Activating Token Index: 903

Text #10

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.8473. Min Act: -0.0002

Data Index: 1579065 (Python Code)

Max Activating Token Index: 920

Text #11

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.8394. Min Act: -0.0002

Data Index: 1521531 (Python Code)

Max Activating Token Index: 850

Text #12

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.9002. Min Act: -0.0002

Data Index: 1599835 (Python Code)

Max Activating Token Index: 955

Text #13

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.9263. Min Act: -0.0002

Data Index: 1532451 (Python Code)

Max Activating Token Index: 875

Text #14

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.8404. Min Act: -0.0002

Data Index: 1397925 (Python Code)

Max Activating Token Index: 895

Text #15

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.9095. Min Act: -0.0002

Data Index: 1433228 (Python Code)

Max Activating Token Index: 902

Text #16

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.9307. Min Act: -0.0002

Data Index: 1432179 (Python Code)

Max Activating Token Index: 880

Text #17

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.8454. Min Act: -0.0002

Data Index: 1369017 (Python Code)

Max Activating Token Index: 796

Text #18

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.8538. Min Act: -0.0002

Data Index: 1408272 (Python Code)

Max Activating Token Index: 701

Text #19

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.8549. Min Act: -0.0002

Data Index: 1510146 (Python Code)

Max Activating Token Index: 858