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

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

Neuron 664 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: 0.6415. Min Range: -0.6415

Max Act: 0.6415. Min Act: -0.0000

Data Index: 1203501 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.5837. Min Act: -0.0001

Data Index: 250188 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.5995. Min Act: -0.0001

Data Index: 153788 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.5375. Min Act: -0.0001

Data Index: 423811 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.5124. Min Act: -0.0000

Data Index: 886681 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4658. Min Act: -0.0001

Data Index: 596224 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4993. Min Act: -0.0001

Data Index: 1240732 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4461. Min Act: -0.0001

Data Index: 582899 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4315. Min Act: -0.0001

Data Index: 401536 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4587. Min Act: -0.0000

Data Index: 935608 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4694. Min Act: -0.0000

Data Index: 60264 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4487. Min Act: -0.0001

Data Index: 1111731 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4316. Min Act: -0.0000

Data Index: 348113 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.3995. Min Act: -0.0000

Data Index: 21169 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4392. Min Act: -0.0000

Data Index: 491713 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4483. Min Act: -0.0000

Data Index: 365859 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4065. Min Act: -0.0000

Data Index: 492224 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4141. Min Act: -0.0001

Data Index: 117758 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.4143. Min Act: -0.0001

Data Index: 661989 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.6415. Min Range: -0.6415

Max Act: 0.3965. Min Act: -0.0000

Data Index: 774393 (C4 (Web Text))

Max Activating Token Index: 395