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

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

Neuron 3017 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.4568. Min Act: -0.0000

Data Index: 810883 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.1867. Min Act: -0.0000

Data Index: 1472176 (Python Code)

Max Activating Token Index: 256

Text #2

Max Range: 3.4568. Min Range: -3.4568

Max Act: 2.6683. Min Act: -0.0000

Data Index: 133669 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 3.4568. Min Range: -3.4568

Max Act: 2.8466. Min Act: -0.0000

Data Index: 530435 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 3.4568. Min Range: -3.4568

Max Act: 2.7348. Min Act: -0.0000

Data Index: 1193408 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 3.4568. Min Range: -3.4568

Max Act: 2.7463. Min Act: -0.0000

Data Index: 1386893 (Python Code)

Max Activating Token Index: 492

Text #6

Max Range: 3.4568. Min Range: -3.4568

Max Act: 2.6934. Min Act: -0.0000

Data Index: 1061768 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 3.4568. Min Range: -3.4568

Max Act: 2.6756. Min Act: -0.0000

Data Index: 841026 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 3.4568. Min Range: -3.4568

Max Act: 2.5150. Min Act: -0.0000

Data Index: 612119 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 3.4568. Min Range: -3.4568

Max Act: 2.4648. Min Act: -0.0000

Data Index: 741853 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 3.4568. Min Range: -3.4568

Max Act: 2.5757. Min Act: -0.0000

Data Index: 130336 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 3.4568. Min Range: -3.4568

Max Act: 2.5861. Min Act: -0.0000

Data Index: 1469051 (Python Code)

Max Activating Token Index: 123

Text #12

Max Range: 3.4568. Min Range: -3.4568

Max Act: 2.6861. Min Act: -0.0000

Data Index: 1152204 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 3.4568. Min Range: -3.4568

Max Act: 2.4641. Min Act: -0.0000

Data Index: 133044 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 3.4568. Min Range: -3.4568

Max Act: 2.5123. Min Act: -0.0000

Data Index: 1371000 (Python Code)

Max Activating Token Index: 975

Text #15

Max Range: 3.4568. Min Range: -3.4568

Max Act: 2.3929. Min Act: -0.0000

Data Index: 1023337 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 3.4568. Min Range: -3.4568

Max Act: 2.2568. Min Act: -0.0000

Data Index: 1073096 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 3.4568. Min Range: -3.4568

Max Act: 2.3457. Min Act: -0.0000

Data Index: 1437920 (Python Code)

Max Activating Token Index: 841

Text #18

Max Range: 3.4568. Min Range: -3.4568

Max Act: 2.3312. Min Act: -0.0000

Data Index: 1017584 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 3.4568. Min Range: -3.4568

Max Act: 2.3205. Min Act: -0.0000

Data Index: 1394438 (Python Code)

Max Activating Token Index: 528