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

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

Neuron 2650 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.5088. Min Act: -0.0001

Data Index: 671013 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3922. Min Act: -0.0001

Data Index: 902961 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4067. Min Act: -0.0001

Data Index: 203027 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3793. Min Act: -0.0001

Data Index: 1021023 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3640. Min Act: -0.0001

Data Index: 1337038 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3507. Min Act: -0.0001

Data Index: 1113758 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3591. Min Act: -0.0001

Data Index: 1264282 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3456. Min Act: -0.0001

Data Index: 1274615 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3437. Min Act: -0.0001

Data Index: 1074986 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3627. Min Act: -0.0001

Data Index: 1003302 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3531. Min Act: -0.0001

Data Index: 171194 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3379. Min Act: -0.0001

Data Index: 1246317 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3410. Min Act: -0.0001

Data Index: 1320111 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3411. Min Act: -0.0001

Data Index: 995833 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3271. Min Act: -0.0001

Data Index: 29312 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3203. Min Act: -0.0001

Data Index: 632225 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3225. Min Act: -0.0001

Data Index: 686530 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3464. Min Act: -0.0001

Data Index: 958577 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3672. Min Act: -0.0001

Data Index: 1174451 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3228. Min Act: -0.0001

Data Index: 1063285 (C4 (Web Text))

Max Activating Token Index: 70