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

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

Neuron 3328 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: 0.0976. Min Range: -0.0976

Max Act: 0.0967. Min Act: -0.0002

Data Index: 135538 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0963. Min Act: -0.0002

Data Index: 298892 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0976. Min Act: -0.0002

Data Index: 695577 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0943. Min Act: -0.0002

Data Index: 992551 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0922. Min Act: -0.0002

Data Index: 1249636 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1085354 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0906. Min Act: -0.0002

Data Index: 218314 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0930. Min Act: -0.0002

Data Index: 803329 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0897. Min Act: -0.0002

Data Index: 1044449 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0907. Min Act: -0.0002

Data Index: 321581 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0924. Min Act: -0.0002

Data Index: 1124416 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0887. Min Act: -0.0002

Data Index: 487000 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0901. Min Act: -0.0002

Data Index: 442488 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1249231 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0876. Min Act: -0.0002

Data Index: 452202 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0903. Min Act: -0.0002

Data Index: 1118873 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0885. Min Act: -0.0002

Data Index: 970353 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0883. Min Act: -0.0002

Data Index: 554878 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0873. Min Act: -0.0002

Data Index: 160279 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0888. Min Act: -0.0002

Data Index: 76613 (C4 (Web Text))

Max Activating Token Index: 42