Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1016 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5740. Min Act: -0.0001

Data Index: 358418 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5336. Min Act: -0.0001

Data Index: 1262956 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.6050. Min Act: -0.0001

Data Index: 1268906 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.3983. Min Act: -0.0001

Data Index: 482558 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5899. Min Act: -0.0001

Data Index: 82365 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5754. Min Act: -0.0001

Data Index: 481643 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5107. Min Act: -0.0001

Data Index: 1036895 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5471. Min Act: -0.0001

Data Index: 318002 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5287. Min Act: -0.0001

Data Index: 746027 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.3855. Min Act: -0.0001

Data Index: 967774 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4852. Min Act: -0.0001

Data Index: 1000606 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5171. Min Act: -0.0001

Data Index: 958459 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5403. Min Act: -0.0001

Data Index: 116439 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4950. Min Act: -0.0001

Data Index: 236135 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5031. Min Act: -0.0001

Data Index: 28014 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5139. Min Act: -0.0001

Data Index: 1035005 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4652. Min Act: -0.0001

Data Index: 652044 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5075. Min Act: -0.0001

Data Index: 1279901 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4440. Min Act: -0.0001

Data Index: 1193361 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4459. Min Act: -0.0001

Data Index: 236664 (C4 (Web Text))

Max Activating Token Index: 371