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

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

Neuron 211 in Layer 0

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: 1.3930. Min Range: -1.3930

Max Act: 1.3930. Min Act: -0.0001

Data Index: 1002824 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.3930. Min Act: -0.0001

Data Index: 1197873 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.3930. Min Act: -0.0001

Data Index: 679546 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.3930. Min Act: -0.0001

Data Index: 1165326 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.3930. Min Act: -0.0001

Data Index: 308184 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.3930. Min Act: -0.0001

Data Index: 320138 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.3930. Min Act: -0.0001

Data Index: 1297560 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.3930. Min Act: -0.0001

Data Index: 942539 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.3930. Min Act: -0.0002

Data Index: 210048 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.3930. Min Act: -0.0001

Data Index: 102653 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.3930. Min Act: -0.0001

Data Index: 483649 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.3930. Min Act: -0.0001

Data Index: 388489 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.3930. Min Act: -0.0001

Data Index: 1021776 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.3930. Min Act: -0.0001

Data Index: 696422 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.3930. Min Act: -0.0001

Data Index: 550783 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.3010. Min Act: -0.0001

Data Index: 50173 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.3053. Min Act: -0.0001

Data Index: 33973 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.2737. Min Act: -0.0001

Data Index: 1297402 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.2680. Min Act: -0.0001

Data Index: 797015 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.2680. Min Act: -0.0001

Data Index: 763669 (C4 (Web Text))

Max Activating Token Index: 3