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

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

Neuron 2223 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.8266. Min Act: -0.0000

Data Index: 839284 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.4345. Min Act: -0.0000

Data Index: 1157777 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.2250. Min Act: -0.0000

Data Index: 556105 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.1357. Min Act: -0.0000

Data Index: 857510 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.1052. Min Act: -0.0000

Data Index: 686966 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.1293. Min Act: -0.0000

Data Index: 846492 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.0978. Min Act: -0.0000

Data Index: 681702 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 1.8266. Min Range: -1.8266

Max Act: 0.9121. Min Act: 0.0000

Data Index: 1180400 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 1.8266. Min Range: -1.8266

Max Act: 0.9159. Min Act: -0.0000

Data Index: 899095 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 1.8266. Min Range: -1.8266

Max Act: 0.9631. Min Act: -0.0000

Data Index: 610099 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.0228. Min Act: -0.0000

Data Index: 255907 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 1.8266. Min Range: -1.8266

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1122064 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 1.8266. Min Range: -1.8266

Max Act: 1.0235. Min Act: -0.0000

Data Index: 185382 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 1.8266. Min Range: -1.8266

Max Act: 0.9398. Min Act: -0.0000

Data Index: 60199 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 1.8266. Min Range: -1.8266

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1178890 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 1.8266. Min Range: -1.8266

Max Act: 0.9060. Min Act: -0.0000

Data Index: 189 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 1.8266. Min Range: -1.8266

Max Act: 0.9521. Min Act: -0.0000

Data Index: 558022 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 1.8266. Min Range: -1.8266

Max Act: 0.9011. Min Act: -0.0000

Data Index: 1025019 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 1.8266. Min Range: -1.8266

Max Act: 0.9577. Min Act: -0.0000

Data Index: 424426 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 1.8266. Min Range: -1.8266

Max Act: 0.9489. Min Act: -0.0000

Data Index: 704195 (C4 (Web Text))

Max Activating Token Index: 302