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

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

Neuron 2848 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: 1.1950. Min Range: -1.1950

Max Act: 1.1950. Min Act: -0.0003

Data Index: 1197810 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 1.1950. Min Range: -1.1950

Max Act: 1.1449. Min Act: -0.0003

Data Index: 149581 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 1.1950. Min Range: -1.1950

Max Act: 1.1137. Min Act: -0.0003

Data Index: 501680 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 1.1950. Min Range: -1.1950

Max Act: 1.0549. Min Act: -0.0002

Data Index: 580633 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 1.1950. Min Range: -1.1950

Max Act: 1.0659. Min Act: -0.0002

Data Index: 691828 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 1.1950. Min Range: -1.1950

Max Act: 1.0864. Min Act: -0.0003

Data Index: 892837 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 1.1950. Min Range: -1.1950

Max Act: 1.0560. Min Act: -0.0002

Data Index: 178719 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 1.1950. Min Range: -1.1950

Max Act: 1.0275. Min Act: -0.0003

Data Index: 428994 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 1.1950. Min Range: -1.1950

Max Act: 1.0302. Min Act: -0.0002

Data Index: 993645 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.9740. Min Act: -0.0003

Data Index: 1152688 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.9689. Min Act: -0.0002

Data Index: 1274314 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.9668. Min Act: -0.0003

Data Index: 961790 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.9525. Min Act: -0.0003

Data Index: 112952 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.9669. Min Act: -0.0002

Data Index: 1212903 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.9647. Min Act: -0.0002

Data Index: 783608 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.9542. Min Act: -0.0003

Data Index: 1104253 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.9287. Min Act: -0.0003

Data Index: 1095578 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.9247. Min Act: -0.0003

Data Index: 1208846 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.9098. Min Act: -0.0003

Data Index: 329237 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 1.1950. Min Range: -1.1950

Max Act: 0.9053. Min Act: -0.0002

Data Index: 7951 (C4 (Web Text))

Max Activating Token Index: 40