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

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

Neuron 2789 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: 1.2963. Min Range: -1.2963

Max Act: 1.2963. Min Act: -0.0002

Data Index: 1163837 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0952. Min Act: -0.0002

Data Index: 927956 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0790. Min Act: -0.0002

Data Index: 666283 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0702. Min Act: -0.0003

Data Index: 1012138 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0472. Min Act: -0.0002

Data Index: 998835 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0622. Min Act: -0.0002

Data Index: 615622 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0366. Min Act: -0.0002

Data Index: 730951 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0335. Min Act: -0.0002

Data Index: 851529 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0230. Min Act: -0.0002

Data Index: 951971 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0266. Min Act: -0.0002

Data Index: 824870 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0161. Min Act: -0.0002

Data Index: 631623 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0478. Min Act: -0.0002

Data Index: 826846 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0122. Min Act: -0.0002

Data Index: 846576 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0209. Min Act: -0.0002

Data Index: 671233 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0150. Min Act: -0.0002

Data Index: 1096296 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0222. Min Act: -0.0002

Data Index: 653574 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0250. Min Act: -0.0002

Data Index: 995467 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0150. Min Act: -0.0002

Data Index: 1157764 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0189. Min Act: -0.0002

Data Index: 350309 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 1.2963. Min Range: -1.2963

Max Act: 1.0120. Min Act: -0.0002

Data Index: 370652 (C4 (Web Text))

Max Activating Token Index: 879