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

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

Neuron 892 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.6147. Min Act: -0.0001

Data Index: 1400001 (Python Code)

Max Activating Token Index: 479

Text #1

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.5924. Min Act: -0.0001

Data Index: 1414566 (Python Code)

Max Activating Token Index: 539

Text #2

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.5976. Min Act: -0.0001

Data Index: 1532511 (Python Code)

Max Activating Token Index: 209

Text #3

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.5883. Min Act: -0.0001

Data Index: 1391192 (Python Code)

Max Activating Token Index: 443

Text #4

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.5522. Min Act: -0.0001

Data Index: 1532457 (Python Code)

Max Activating Token Index: 930

Text #5

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.5933. Min Act: -0.0001

Data Index: 1460575 (Python Code)

Max Activating Token Index: 610

Text #6

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.5151. Min Act: -0.0001

Data Index: 1545556 (Python Code)

Max Activating Token Index: 592

Text #7

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.5081. Min Act: -0.0001

Data Index: 1429183 (Python Code)

Max Activating Token Index: 361

Text #8

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4977. Min Act: -0.0001

Data Index: 1602146 (Python Code)

Max Activating Token Index: 350

Text #9

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4702. Min Act: -0.0001

Data Index: 1436239 (Python Code)

Max Activating Token Index: 892

Text #10

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4813. Min Act: -0.0001

Data Index: 1375818 (Python Code)

Max Activating Token Index: 378

Text #11

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4767. Min Act: -0.0001

Data Index: 1608839 (Python Code)

Max Activating Token Index: 788

Text #12

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4612. Min Act: -0.0001

Data Index: 1620580 (Python Code)

Max Activating Token Index: 461

Text #13

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4403. Min Act: -0.0001

Data Index: 1621851 (Python Code)

Max Activating Token Index: 200

Text #14

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4735. Min Act: -0.0001

Data Index: 1379171 (Python Code)

Max Activating Token Index: 657

Text #15

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4512. Min Act: -0.0001

Data Index: 1366217 (Python Code)

Max Activating Token Index: 225

Text #16

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4810. Min Act: -0.0001

Data Index: 1575351 (Python Code)

Max Activating Token Index: 294

Text #17

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4165. Min Act: -0.0001

Data Index: 1486945 (Python Code)

Max Activating Token Index: 788

Text #18

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4391. Min Act: -0.0001

Data Index: 1444244 (Python Code)

Max Activating Token Index: 131

Text #19

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4340. Min Act: -0.0001

Data Index: 1379768 (Python Code)

Max Activating Token Index: 649