Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3561 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7006. Min Range: -0.7006

Max Act: 0.7006. Min Act: -0.0001

Data Index: 1126895 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 0.7006. Min Range: -0.7006

Max Act: 0.6657. Min Act: -0.0001

Data Index: 1042028 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.7006. Min Range: -0.7006

Max Act: 0.6282. Min Act: -0.0001

Data Index: 517797 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.7006. Min Range: -0.7006

Max Act: 0.6273. Min Act: -0.0001

Data Index: 908939 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.7006. Min Range: -0.7006

Max Act: 0.6511. Min Act: -0.0001

Data Index: 25424 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.7006. Min Range: -0.7006

Max Act: 0.5908. Min Act: -0.0001

Data Index: 359432 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.7006. Min Range: -0.7006

Max Act: 0.6093. Min Act: -0.0001

Data Index: 635692 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 0.7006. Min Range: -0.7006

Max Act: 0.5671. Min Act: -0.0001

Data Index: 999191 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 0.7006. Min Range: -0.7006

Max Act: 0.5621. Min Act: -0.0001

Data Index: 540603 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.7006. Min Range: -0.7006

Max Act: 0.5931. Min Act: -0.0001

Data Index: 919677 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.7006. Min Range: -0.7006

Max Act: 0.5018. Min Act: -0.0001

Data Index: 421902 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.7006. Min Range: -0.7006

Max Act: 0.5304. Min Act: -0.0001

Data Index: 741675 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.7006. Min Range: -0.7006

Max Act: 0.5661. Min Act: -0.0001

Data Index: 1114555 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 0.7006. Min Range: -0.7006

Max Act: 0.4894. Min Act: -0.0001

Data Index: 571797 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.7006. Min Range: -0.7006

Max Act: 0.4897. Min Act: -0.0001

Data Index: 1104886 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.7006. Min Range: -0.7006

Max Act: 0.4523. Min Act: -0.0001

Data Index: 74000 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.7006. Min Range: -0.7006

Max Act: 0.4772. Min Act: -0.0001

Data Index: 1327838 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.7006. Min Range: -0.7006

Max Act: 0.4601. Min Act: -0.0001

Data Index: 20357 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.7006. Min Range: -0.7006

Max Act: 0.5059. Min Act: -0.0001

Data Index: 1289542 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.7006. Min Range: -0.7006

Max Act: 0.4943. Min Act: -0.0001

Data Index: 1113518 (C4 (Web Text))

Max Activating Token Index: 89