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

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

Neuron 5043 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4435. Min Range: -4.4435

Max Act: 4.4435. Min Act: -0.0000

Data Index: 12992 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 4.4435. Min Range: -4.4435

Max Act: 3.9191. Min Act: -0.0000

Data Index: 716378 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 4.4435. Min Range: -4.4435

Max Act: 3.8454. Min Act: -0.0000

Data Index: 1127328 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 4.4435. Min Range: -4.4435

Max Act: 3.5061. Min Act: -0.0000

Data Index: 1263781 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 4.4435. Min Range: -4.4435

Max Act: 3.4596. Min Act: -0.0000

Data Index: 1236033 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 4.4435. Min Range: -4.4435

Max Act: 3.5392. Min Act: -0.0000

Data Index: 63731 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 4.4435. Min Range: -4.4435

Max Act: 3.1935. Min Act: -0.0000

Data Index: 758960 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 4.4435. Min Range: -4.4435

Max Act: 2.7053. Min Act: -0.0000

Data Index: 1030982 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 4.4435. Min Range: -4.4435

Max Act: 2.9651. Min Act: -0.0000

Data Index: 913842 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 4.4435. Min Range: -4.4435

Max Act: 2.6636. Min Act: -0.0000

Data Index: 708887 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 4.4435. Min Range: -4.4435

Max Act: 2.6499. Min Act: -0.0000

Data Index: 811332 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 4.4435. Min Range: -4.4435

Max Act: 2.5451. Min Act: -0.0000

Data Index: 359200 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 4.4435. Min Range: -4.4435

Max Act: 2.8072. Min Act: -0.0000

Data Index: 681505 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 4.4435. Min Range: -4.4435

Max Act: 2.5939. Min Act: -0.0000

Data Index: 811878 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 4.4435. Min Range: -4.4435

Max Act: 2.7875. Min Act: -0.0000

Data Index: 624983 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 4.4435. Min Range: -4.4435

Max Act: 2.6344. Min Act: -0.0000

Data Index: 1233114 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 4.4435. Min Range: -4.4435

Max Act: 2.1784. Min Act: -0.0000

Data Index: 174115 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 4.4435. Min Range: -4.4435

Max Act: 2.2705. Min Act: -0.0000

Data Index: 881542 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 4.4435. Min Range: -4.4435

Max Act: 2.2617. Min Act: -0.0000

Data Index: 303942 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 4.4435. Min Range: -4.4435

Max Act: 2.3784. Min Act: -0.0000

Data Index: 457363 (C4 (Web Text))

Max Activating Token Index: 43