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

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

Neuron 1280 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1023384 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1277. Min Act: -0.0000

Data Index: 1127400 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1304. Min Act: -0.0000

Data Index: 212175 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1223. Min Act: -0.0000

Data Index: 412885 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1199. Min Act: -0.0000

Data Index: 758005 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1304627 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1088. Min Act: -0.0000

Data Index: 336726 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1083. Min Act: -0.0001

Data Index: 993169 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1033. Min Act: -0.0000

Data Index: 213650 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1201. Min Act: -0.0000

Data Index: 1371905 (Python Code)

Max Activating Token Index: 77

Text #10

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1072. Min Act: -0.0001

Data Index: 1082352 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1005. Min Act: -0.0001

Data Index: 1254948 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.0997. Min Act: -0.0001

Data Index: 93612 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1054. Min Act: -0.0000

Data Index: 1613353 (Python Code)

Max Activating Token Index: 144

Text #14

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.0964. Min Act: -0.0000

Data Index: 291586 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.0994. Min Act: -0.0001

Data Index: 1074896 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.0979. Min Act: -0.0001

Data Index: 622497 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.0973. Min Act: -0.0000

Data Index: 1172678 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.0914. Min Act: -0.0001

Data Index: 295375 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1052. Min Act: -0.0001

Data Index: 413475 (C4 (Web Text))

Max Activating Token Index: 891