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

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

Neuron 3095 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: 2.5118. Min Range: -2.5118

Max Act: 2.5118. Min Act: -0.0000

Data Index: 589741 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 2.5118. Min Range: -2.5118

Max Act: 1.9464. Min Act: -0.0000

Data Index: 1166082 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 2.5118. Min Range: -2.5118

Max Act: 1.9496. Min Act: -0.0000

Data Index: 590562 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 2.5118. Min Range: -2.5118

Max Act: 1.7209. Min Act: -0.0001

Data Index: 561750 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 2.5118. Min Range: -2.5118

Max Act: 1.7618. Min Act: -0.0000

Data Index: 367758 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 2.5118. Min Range: -2.5118

Max Act: 1.4873. Min Act: -0.0000

Data Index: 950526 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 2.5118. Min Range: -2.5118

Max Act: 1.7344. Min Act: -0.0001

Data Index: 1241177 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 2.5118. Min Range: -2.5118

Max Act: 1.7218. Min Act: -0.0001

Data Index: 1097230 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 2.5118. Min Range: -2.5118

Max Act: 1.6169. Min Act: -0.0000

Data Index: 563025 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 2.5118. Min Range: -2.5118

Max Act: 1.7042. Min Act: -0.0000

Data Index: 483682 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 2.5118. Min Range: -2.5118

Max Act: 1.6003. Min Act: -0.0000

Data Index: 203147 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 2.5118. Min Range: -2.5118

Max Act: 1.7333. Min Act: -0.0000

Data Index: 966898 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 2.5118. Min Range: -2.5118

Max Act: 1.6380. Min Act: -0.0000

Data Index: 984447 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 2.5118. Min Range: -2.5118

Max Act: 1.3808. Min Act: -0.0000

Data Index: 1270368 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 2.5118. Min Range: -2.5118

Max Act: 1.7028. Min Act: -0.0001

Data Index: 502721 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 2.5118. Min Range: -2.5118

Max Act: 1.4891. Min Act: -0.0000

Data Index: 1182630 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 2.5118. Min Range: -2.5118

Max Act: 1.3934. Min Act: -0.0000

Data Index: 34100 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 2.5118. Min Range: -2.5118

Max Act: 1.3993. Min Act: -0.0001

Data Index: 48032 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 2.5118. Min Range: -2.5118

Max Act: 1.4671. Min Act: -0.0001

Data Index: 283311 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 2.5118. Min Range: -2.5118

Max Act: 1.5458. Min Act: -0.0000

Data Index: 1188951 (C4 (Web Text))

Max Activating Token Index: 739