Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3974 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.5333. Min Act: -0.0001

Data Index: 1023142 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.3280. Min Act: -0.0000

Data Index: 573864 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1967 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 1.5333. Min Range: -1.5333

Max Act: 0.9364. Min Act: -0.0001

Data Index: 100843 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 1.5333. Min Range: -1.5333

Max Act: 0.9151. Min Act: -0.0001

Data Index: 52068 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 1.5333. Min Range: -1.5333

Max Act: 0.8921. Min Act: -0.0001

Data Index: 113952 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 1.5333. Min Range: -1.5333

Max Act: 0.8691. Min Act: -0.0001

Data Index: 644128 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 1.5333. Min Range: -1.5333

Max Act: 0.9077. Min Act: -0.0000

Data Index: 705551 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 1.5333. Min Range: -1.5333

Max Act: 0.9046. Min Act: -0.0000

Data Index: 939210 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 1.5333. Min Range: -1.5333

Max Act: 0.8652. Min Act: -0.0000

Data Index: 487701 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 1.5333. Min Range: -1.5333

Max Act: 0.8621. Min Act: -0.0000

Data Index: 646963 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 1.5333. Min Range: -1.5333

Max Act: 0.8801. Min Act: -0.0001

Data Index: 1275540 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 1.5333. Min Range: -1.5333

Max Act: 0.8677. Min Act: -0.0000

Data Index: 46563 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 1.5333. Min Range: -1.5333

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1342606 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 1.5333. Min Range: -1.5333

Max Act: 0.8150. Min Act: -0.0001

Data Index: 315978 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 1.5333. Min Range: -1.5333

Max Act: 0.8370. Min Act: -0.0000

Data Index: 878777 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 1.5333. Min Range: -1.5333

Max Act: 0.8609. Min Act: -0.0000

Data Index: 176694 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 1.5333. Min Range: -1.5333

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1232289 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 1.5333. Min Range: -1.5333

Max Act: 0.8322. Min Act: -0.0001

Data Index: 622627 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 1.5333. Min Range: -1.5333

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1201080 (C4 (Web Text))

Max Activating Token Index: 552