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

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

Neuron 3005 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4799. Min Range: -0.4799

Max Act: 0.4661. Min Act: -0.0002

Data Index: 294657 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.4799. Min Range: -0.4799

Max Act: 0.4799. Min Act: -0.0002

Data Index: 37527 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.4799. Min Range: -0.4799

Max Act: 0.4271. Min Act: -0.0001

Data Index: 1005846 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.4799. Min Range: -0.4799

Max Act: 0.4093. Min Act: -0.0001

Data Index: 1155207 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.4799. Min Range: -0.4799

Max Act: 0.4078. Min Act: -0.0001

Data Index: 540072 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.4799. Min Range: -0.4799

Max Act: 0.3784. Min Act: -0.0002

Data Index: 756930 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 0.4799. Min Range: -0.4799

Max Act: 0.3646. Min Act: -0.0001

Data Index: 799967 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.4799. Min Range: -0.4799

Max Act: 0.3720. Min Act: -0.0001

Data Index: 508943 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 0.4799. Min Range: -0.4799

Max Act: 0.3583. Min Act: -0.0001

Data Index: 771853 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.4799. Min Range: -0.4799

Max Act: 0.3230. Min Act: -0.0001

Data Index: 858437 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 0.4799. Min Range: -0.4799

Max Act: 0.3317. Min Act: -0.0001

Data Index: 19297 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.4799. Min Range: -0.4799

Max Act: 0.3188. Min Act: -0.0002

Data Index: 956285 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.4799. Min Range: -0.4799

Max Act: 0.3292. Min Act: -0.0001

Data Index: 613597 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.4799. Min Range: -0.4799

Max Act: 0.3256. Min Act: -0.0002

Data Index: 16049 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.4799. Min Range: -0.4799

Max Act: 0.3048. Min Act: -0.0001

Data Index: 557147 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.4799. Min Range: -0.4799

Max Act: 0.3151. Min Act: -0.0002

Data Index: 280940 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.4799. Min Range: -0.4799

Max Act: 0.2992. Min Act: -0.0001

Data Index: 334878 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.4799. Min Range: -0.4799

Max Act: 0.3105. Min Act: -0.0001

Data Index: 765124 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.4799. Min Range: -0.4799

Max Act: 0.3168. Min Act: -0.0001

Data Index: 342205 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.4799. Min Range: -0.4799

Max Act: 0.3042. Min Act: -0.0002

Data Index: 518466 (C4 (Web Text))

Max Activating Token Index: 2