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

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

Neuron 1127 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: 1.8081. Min Range: -1.8081

Max Act: 1.8081. Min Act: -0.0002

Data Index: 107505 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.7258. Min Act: -0.0002

Data Index: 739503 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.4458. Min Act: -0.0002

Data Index: 1132706 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.3745. Min Act: -0.0002

Data Index: 882845 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.3687. Min Act: -0.0002

Data Index: 708508 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.3798. Min Act: -0.0002

Data Index: 514480 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.3466. Min Act: -0.0002

Data Index: 1121999 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.3652. Min Act: -0.0003

Data Index: 889478 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.3515. Min Act: -0.0002

Data Index: 1108289 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.3230. Min Act: -0.0002

Data Index: 456713 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.3419. Min Act: -0.0002

Data Index: 341056 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.3565. Min Act: -0.0002

Data Index: 779108 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.3254. Min Act: -0.0002

Data Index: 692128 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.2994. Min Act: -0.0002

Data Index: 136726 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.3102. Min Act: -0.0002

Data Index: 473479 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.3132. Min Act: -0.0003

Data Index: 864724 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.3123. Min Act: -0.0002

Data Index: 842827 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.2920. Min Act: -0.0002

Data Index: 401305 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.2900. Min Act: -0.0002

Data Index: 685144 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 1.8081. Min Range: -1.8081

Max Act: 1.2879. Min Act: -0.0002

Data Index: 1255524 (C4 (Web Text))

Max Activating Token Index: 940