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

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

Neuron 5801 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.4465. Min Act: -0.0000

Data Index: 998686 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3829. Min Act: -0.0000

Data Index: 431668 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1238839 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3169. Min Act: -0.0000

Data Index: 96322 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3347. Min Act: -0.0000

Data Index: 804796 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3323. Min Act: -0.0000

Data Index: 356057 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3255. Min Act: -0.0000

Data Index: 362270 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3140. Min Act: -0.0000

Data Index: 972957 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3069. Min Act: -0.0000

Data Index: 929745 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.2885. Min Act: -0.0000

Data Index: 1161481 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3266. Min Act: -0.0000

Data Index: 423455 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1128247 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3217. Min Act: -0.0000

Data Index: 363549 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3010. Min Act: -0.0000

Data Index: 860993 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3123. Min Act: -0.0000

Data Index: 1245351 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3084. Min Act: -0.0000

Data Index: 878467 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.2895. Min Act: -0.0000

Data Index: 680020 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.2970. Min Act: -0.0000

Data Index: 30127 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.2944. Min Act: -0.0000

Data Index: 913871 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.2955. Min Act: -0.0000

Data Index: 1274577 (C4 (Web Text))

Max Activating Token Index: 567