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

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

Neuron 2394 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.4874. Min Act: -0.0001

Data Index: 310111 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.4874. Min Range: -4.4874

Max Act: 4.0096. Min Act: -0.0001

Data Index: 64443 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.4874. Min Range: -4.4874

Max Act: 3.5764. Min Act: -0.0001

Data Index: 1259154 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.4874. Min Range: -4.4874

Max Act: 3.3624. Min Act: -0.0001

Data Index: 1291418 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.4874. Min Range: -4.4874

Max Act: 3.5961. Min Act: -0.0001

Data Index: 392150 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 4.4874. Min Range: -4.4874

Max Act: 3.4042. Min Act: -0.0001

Data Index: 1602806 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 4.4874. Min Range: -4.4874

Max Act: 2.6040. Min Act: -0.0001

Data Index: 330777 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 4.4874. Min Range: -4.4874

Max Act: 3.0602. Min Act: -0.0001

Data Index: 1291343 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 4.4874. Min Range: -4.4874

Max Act: 3.3004. Min Act: -0.0001

Data Index: 1054509 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.4874. Min Range: -4.4874

Max Act: 2.7430. Min Act: -0.0001

Data Index: 1003105 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.4874. Min Range: -4.4874

Max Act: 2.3184. Min Act: -0.0001

Data Index: 1605502 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 4.4874. Min Range: -4.4874

Max Act: 2.7106. Min Act: -0.0001

Data Index: 1195507 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 4.4874. Min Range: -4.4874

Max Act: 2.7790. Min Act: -0.0001

Data Index: 295086 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.4874. Min Range: -4.4874

Max Act: 2.8896. Min Act: -0.0001

Data Index: 1467724 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 4.4874. Min Range: -4.4874

Max Act: 2.7372. Min Act: -0.0001

Data Index: 1070052 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 4.4874. Min Range: -4.4874

Max Act: 2.6417. Min Act: -0.0001

Data Index: 1584783 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 4.4874. Min Range: -4.4874

Max Act: 2.9860. Min Act: -0.0001

Data Index: 6403 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 4.4874. Min Range: -4.4874

Max Act: 2.6624. Min Act: -0.0001

Data Index: 225522 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 4.4874. Min Range: -4.4874

Max Act: 2.8133. Min Act: -0.0001

Data Index: 1187727 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 4.4874. Min Range: -4.4874

Max Act: 2.7332. Min Act: -0.0001

Data Index: 1650772 (Python Code)

Max Activating Token Index: 1023