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

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

Neuron 2339 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: 0.4213. Min Range: -0.4213

Max Act: 0.4213. Min Act: 0.0001

Data Index: 1436345 (Python Code)

Max Activating Token Index: 58

Text #1

Max Range: 0.4213. Min Range: -0.4213

Max Act: 0.3778. Min Act: -0.0001

Data Index: 1571703 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 0.4213. Min Range: -0.4213

Max Act: 0.3429. Min Act: -0.0000

Data Index: 822431 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.4213. Min Range: -0.4213

Max Act: 0.3268. Min Act: 0.0001

Data Index: 102507 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.4213. Min Range: -0.4213

Max Act: 0.3205. Min Act: -0.0000

Data Index: 249770 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.4213. Min Range: -0.4213

Max Act: 0.3274. Min Act: 0.0001

Data Index: 938171 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 0.4213. Min Range: -0.4213

Max Act: 0.3272. Min Act: 0.0000

Data Index: 1429738 (Python Code)

Max Activating Token Index: 698

Text #7

Max Range: 0.4213. Min Range: -0.4213

Max Act: 0.3140. Min Act: -0.0000

Data Index: 655121 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 0.4213. Min Range: -0.4213

Max Act: 0.3454. Min Act: -0.0001

Data Index: 910821 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 0.4213. Min Range: -0.4213

Max Act: 0.3104. Min Act: 0.0000

Data Index: 430852 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.4213. Min Range: -0.4213

Max Act: 0.3171. Min Act: 0.0000

Data Index: 1371455 (Python Code)

Max Activating Token Index: 147

Text #11

Max Range: 0.4213. Min Range: -0.4213

Max Act: 0.3259. Min Act: -0.0000

Data Index: 939290 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.4213. Min Range: -0.4213

Max Act: 0.3050. Min Act: -0.0000

Data Index: 552629 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.4213. Min Range: -0.4213

Max Act: 0.3038. Min Act: -0.0001

Data Index: 346234 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.4213. Min Range: -0.4213

Max Act: 0.3039. Min Act: 0.0000

Data Index: 1636282 (Python Code)

Max Activating Token Index: 145

Text #15

Max Range: 0.4213. Min Range: -0.4213

Max Act: 0.2701. Min Act: -0.0001

Data Index: 1240218 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.4213. Min Range: -0.4213

Max Act: 0.2822. Min Act: -0.0000

Data Index: 161181 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 0.4213. Min Range: -0.4213

Max Act: 0.2927. Min Act: -0.0001

Data Index: 1319054 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 0.4213. Min Range: -0.4213

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1045005 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 0.4213. Min Range: -0.4213

Max Act: 0.2887. Min Act: 0.0003

Data Index: 786678 (C4 (Web Text))

Max Activating Token Index: 469