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

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

Neuron 4170 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1343752 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.7942. Min Act: -0.0000

Data Index: 563917 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6551. Min Act: -0.0000

Data Index: 767505 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1495089 (Python Code)

Max Activating Token Index: 605

Text #4

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.4826. Min Act: -0.0000

Data Index: 906211 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.5557. Min Act: -0.0000

Data Index: 168991 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.5598. Min Act: -0.0000

Data Index: 503537 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.4935. Min Act: -0.0000

Data Index: 153854 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.4979. Min Act: -0.0000

Data Index: 670544 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.4663. Min Act: -0.0000

Data Index: 88934 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.4366. Min Act: -0.0000

Data Index: 308559 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.4450. Min Act: -0.0000

Data Index: 708172 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.4389. Min Act: -0.0000

Data Index: 166308 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.4776. Min Act: -0.0000

Data Index: 470242 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.4533. Min Act: -0.0000

Data Index: 865382 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.4449. Min Act: -0.0000

Data Index: 643424 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.4329. Min Act: -0.0000

Data Index: 96102 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.4195. Min Act: -0.0000

Data Index: 574770 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.4340. Min Act: -0.0000

Data Index: 499088 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.4186. Min Act: -0.0000

Data Index: 32276 (C4 (Web Text))

Max Activating Token Index: 421