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

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

Neuron 6069 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: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 636787 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 953579 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 74462 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 1003765 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 858756 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 414328 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 354216 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 224530 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 867417 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 251375 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 220259 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 586621 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 1295264 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 72781 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 562875 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 473442 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 629383 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1357575 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 529483 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1406394 (Python Code)

Max Activating Token Index: 542