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

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

Neuron 1299 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.6211. Min Act: -0.0000

Data Index: 434392 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.5409. Min Act: -0.0000

Data Index: 574918 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4878. Min Act: -0.0001

Data Index: 796830 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4714. Min Act: -0.0000

Data Index: 1218430 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4538. Min Act: -0.0000

Data Index: 898046 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4500. Min Act: -0.0001

Data Index: 271307 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4161. Min Act: -0.0001

Data Index: 435745 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4387. Min Act: -0.0001

Data Index: 1289452 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4338. Min Act: -0.0000

Data Index: 40167 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4252. Min Act: -0.0001

Data Index: 744109 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4058. Min Act: -0.0000

Data Index: 336918 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4057. Min Act: -0.0000

Data Index: 326287 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4184. Min Act: -0.0000

Data Index: 717689 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.3937. Min Act: -0.0000

Data Index: 523788 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4070. Min Act: -0.0000

Data Index: 88948 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4048. Min Act: -0.0000

Data Index: 1167898 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.3884. Min Act: -0.0000

Data Index: 572750 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.3881. Min Act: -0.0000

Data Index: 1188382 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.3747. Min Act: -0.0001

Data Index: 1156348 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.3870. Min Act: -0.0000

Data Index: 796446 (C4 (Web Text))

Max Activating Token Index: 551