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

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

Neuron 6068 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: 1.1925. Min Range: -1.1925

Max Act: 1.1925. Min Act: -0.0002

Data Index: 1580376 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.1338. Min Act: -0.0002

Data Index: 196930 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.1010. Min Act: -0.0002

Data Index: 884508 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0656. Min Act: -0.0002

Data Index: 889101 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0438. Min Act: -0.0002

Data Index: 780105 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0471. Min Act: -0.0002

Data Index: 1261042 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0460. Min Act: -0.0002

Data Index: 1253653 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0239. Min Act: -0.0002

Data Index: 233434 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0151. Min Act: -0.0002

Data Index: 1472014 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0067. Min Act: -0.0002

Data Index: 1097571 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0142. Min Act: -0.0002

Data Index: 1654540 (Python Code)

Max Activating Token Index: 19

Text #11

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0093. Min Act: -0.0002

Data Index: 359968 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0051. Min Act: -0.0002

Data Index: 1498027 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9875. Min Act: -0.0002

Data Index: 1581931 (Python Code)

Max Activating Token Index: 16

Text #14

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9932. Min Act: -0.0002

Data Index: 1509558 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9861. Min Act: -0.0002

Data Index: 1376168 (Python Code)

Max Activating Token Index: 18

Text #16

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9846. Min Act: -0.0002

Data Index: 526259 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9820. Min Act: -0.0002

Data Index: 1359849 (Python Code)

Max Activating Token Index: 399

Text #18

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9658. Min Act: -0.0002

Data Index: 1452316 (Python Code)

Max Activating Token Index: 16

Text #19

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9946. Min Act: -0.0002

Data Index: 1446820 (Python Code)

Max Activating Token Index: 4