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

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

Neuron 878 in Layer 1

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: 1.2655. Min Range: -1.2655

Max Act: 1.2655. Min Act: -0.0002

Data Index: 1356023 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1863. Min Act: -0.0002

Data Index: 575095 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1677. Min Act: -0.0002

Data Index: 360803 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1782. Min Act: -0.0002

Data Index: 1325242 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1674. Min Act: -0.0002

Data Index: 742850 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1268. Min Act: -0.0002

Data Index: 1117541 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1612. Min Act: -0.0002

Data Index: 1033442 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1345. Min Act: -0.0002

Data Index: 799323 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1307. Min Act: -0.0002

Data Index: 1008150 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1252. Min Act: -0.0002

Data Index: 20669 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1384. Min Act: -0.0002

Data Index: 63446 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1208. Min Act: -0.0002

Data Index: 1066583 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.0977. Min Act: -0.0002

Data Index: 414650 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1221. Min Act: -0.0002

Data Index: 112786 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1054. Min Act: -0.0002

Data Index: 959317 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1171. Min Act: -0.0002

Data Index: 1359111 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1143. Min Act: -0.0002

Data Index: 495802 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1103. Min Act: -0.0002

Data Index: 814687 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.0984. Min Act: -0.0002

Data Index: 1332149 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.0843. Min Act: -0.0002

Data Index: 1056173 (C4 (Web Text))

Max Activating Token Index: 58