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

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

Neuron 5468 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: 0.0973. Min Range: -0.0973

Max Act: 0.0973. Min Act: -0.0002

Data Index: 1635586 (Python Code)

Max Activating Token Index: 223

Text #1

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0972. Min Act: -0.0002

Data Index: 1201342 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0968. Min Act: -0.0002

Data Index: 1611450 (Python Code)

Max Activating Token Index: 499

Text #3

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0925. Min Act: -0.0002

Data Index: 659225 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0928. Min Act: -0.0002

Data Index: 1307329 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0906. Min Act: -0.0002

Data Index: 1159074 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0915. Min Act: -0.0002

Data Index: 615541 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0935. Min Act: -0.0002

Data Index: 141223 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0905. Min Act: -0.0002

Data Index: 19213 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0922. Min Act: -0.0002

Data Index: 848088 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0913. Min Act: -0.0002

Data Index: 1556831 (Python Code)

Max Activating Token Index: 99

Text #11

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0923. Min Act: -0.0002

Data Index: 478662 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0911. Min Act: -0.0002

Data Index: 199827 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0902. Min Act: -0.0003

Data Index: 1017002 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0909. Min Act: -0.0002

Data Index: 383379 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0909. Min Act: -0.0002

Data Index: 652748 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0886. Min Act: -0.0003

Data Index: 38314 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1491852 (Python Code)

Max Activating Token Index: 969

Text #18

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1057220 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0890. Min Act: -0.0002

Data Index: 692138 (C4 (Web Text))

Max Activating Token Index: 289