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

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

Neuron 1417 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: 0.0046. Min Range: -0.0046

Max Act: 0.0046. Min Act: -0.0002

Data Index: 470972 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0046. Min Act: -0.0003

Data Index: 386689 (C4 (Web Text))

Max Activating Token Index: 1

Text #2

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0046. Min Act: -0.0002

Data Index: 1453672 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0046. Min Act: -0.0002

Data Index: 406783 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0046. Min Act: -0.0002

Data Index: 179061 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0042. Min Act: -0.0002

Data Index: 738612 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0042. Min Act: -0.0003

Data Index: 1344422 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0042. Min Act: -0.0002

Data Index: 1156769 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0040. Min Act: -0.0002

Data Index: 1583376 (Python Code)

Max Activating Token Index: 2

Text #9

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0040. Min Act: -0.0002

Data Index: 907711 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1647325 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0037. Min Act: -0.0002

Data Index: 1051533 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0037. Min Act: -0.0002

Data Index: 1325685 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0037. Min Act: -0.0002

Data Index: 52455 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0037. Min Act: -0.0002

Data Index: 1330591 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0037. Min Act: -0.0002

Data Index: 1502368 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0035. Min Act: -0.0002

Data Index: 499659 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0035. Min Act: -0.0002

Data Index: 1645304 (Python Code)

Max Activating Token Index: 2

Text #18

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0035. Min Act: -0.0002

Data Index: 339227 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0035. Min Act: -0.0002

Data Index: 1557249 (Python Code)

Max Activating Token Index: 2