Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2802 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.7337. Min Act: -0.0002

Data Index: 138276 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.7091. Min Act: -0.0001

Data Index: 353078 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.7158. Min Act: -0.0001

Data Index: 1181578 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6952. Min Act: -0.0001

Data Index: 763912 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6863. Min Act: -0.0001

Data Index: 102201 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6401. Min Act: -0.0001

Data Index: 4165 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6401. Min Act: -0.0001

Data Index: 715854 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6347. Min Act: -0.0001

Data Index: 305158 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6338. Min Act: -0.0001

Data Index: 598630 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6240. Min Act: -0.0001

Data Index: 567807 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6244. Min Act: -0.0001

Data Index: 261988 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6060. Min Act: -0.0001

Data Index: 170044 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6118. Min Act: -0.0001

Data Index: 407166 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6019. Min Act: -0.0001

Data Index: 145556 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6141. Min Act: -0.0001

Data Index: 7238 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6050. Min Act: -0.0001

Data Index: 99108 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6016. Min Act: -0.0001

Data Index: 1070918 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6060. Min Act: -0.0001

Data Index: 1006663 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.6124. Min Act: -0.0001

Data Index: 152575 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.7337. Min Range: -0.7337

Max Act: 0.5935. Min Act: -0.0001

Data Index: 106316 (C4 (Web Text))

Max Activating Token Index: 598