Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 617 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3155. Min Range: -2.3155

Max Act: 2.3155. Min Act: -0.0000

Data Index: 468140 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 2.3155. Min Range: -2.3155

Max Act: 2.3069. Min Act: -0.0000

Data Index: 1078777 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 2.3155. Min Range: -2.3155

Max Act: 2.3070. Min Act: -0.0000

Data Index: 157915 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 2.3155. Min Range: -2.3155

Max Act: 2.1788. Min Act: -0.0000

Data Index: 549950 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 2.3155. Min Range: -2.3155

Max Act: 2.1700. Min Act: -0.0000

Data Index: 386849 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 2.3155. Min Range: -2.3155

Max Act: 2.1027. Min Act: -0.0000

Data Index: 629919 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 2.3155. Min Range: -2.3155

Max Act: 2.0529. Min Act: -0.0000

Data Index: 1115609 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 2.3155. Min Range: -2.3155

Max Act: 2.0523. Min Act: -0.0000

Data Index: 383415 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 2.3155. Min Range: -2.3155

Max Act: 2.1060. Min Act: -0.0000

Data Index: 1267915 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 2.3155. Min Range: -2.3155

Max Act: 2.0320. Min Act: -0.0000

Data Index: 117826 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 2.3155. Min Range: -2.3155

Max Act: 1.9814. Min Act: -0.0000

Data Index: 837842 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 2.3155. Min Range: -2.3155

Max Act: 2.0160. Min Act: -0.0000

Data Index: 904875 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 2.3155. Min Range: -2.3155

Max Act: 2.0118. Min Act: -0.0000

Data Index: 1301869 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 2.3155. Min Range: -2.3155

Max Act: 2.0123. Min Act: -0.0000

Data Index: 1054133 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 2.3155. Min Range: -2.3155

Max Act: 1.9535. Min Act: -0.0000

Data Index: 730832 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 2.3155. Min Range: -2.3155

Max Act: 1.9923. Min Act: -0.0000

Data Index: 1317158 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 2.3155. Min Range: -2.3155

Max Act: 1.9303. Min Act: -0.0000

Data Index: 1216348 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 2.3155. Min Range: -2.3155

Max Act: 1.9813. Min Act: -0.0000

Data Index: 954504 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 2.3155. Min Range: -2.3155

Max Act: 1.8783. Min Act: -0.0000

Data Index: 1183177 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 2.3155. Min Range: -2.3155

Max Act: 1.9742. Min Act: -0.0000

Data Index: 234155 (C4 (Web Text))

Max Activating Token Index: 153