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

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

Neuron 3523 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: 1.9771. Min Range: -1.9771

Max Act: 1.9771. Min Act: -0.0002

Data Index: 659707 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.8437. Min Act: -0.0002

Data Index: 30247 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.8688. Min Act: -0.0002

Data Index: 841203 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.7865. Min Act: -0.0002

Data Index: 1046694 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.7814. Min Act: -0.0002

Data Index: 757499 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.7742. Min Act: -0.0002

Data Index: 444788 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.7428. Min Act: -0.0002

Data Index: 1023817 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.7348. Min Act: -0.0002

Data Index: 757290 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.7379. Min Act: -0.0002

Data Index: 754848 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.7336. Min Act: -0.0002

Data Index: 1333072 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.6865. Min Act: -0.0002

Data Index: 223379 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.7221. Min Act: -0.0002

Data Index: 1292696 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.7345. Min Act: -0.0002

Data Index: 164691 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.7593. Min Act: -0.0002

Data Index: 925470 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.7070. Min Act: -0.0002

Data Index: 703942 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.6822. Min Act: -0.0002

Data Index: 49589 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.6930. Min Act: -0.0002

Data Index: 1257969 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.6097. Min Act: -0.0002

Data Index: 374266 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.6666. Min Act: -0.0002

Data Index: 144503 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 1.9771. Min Range: -1.9771

Max Act: 1.6621. Min Act: -0.0002

Data Index: 1135469 (C4 (Web Text))

Max Activating Token Index: 5