Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4628 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.6104. Min Act: -0.0000

Data Index: 350811 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.4440. Min Act: -0.0000

Data Index: 556878 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.3151. Min Act: -0.0000

Data Index: 651247 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.3596. Min Act: -0.0000

Data Index: 1284592 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.1312. Min Act: -0.0000

Data Index: 1087997 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.1267. Min Act: -0.0000

Data Index: 333898 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.1045. Min Act: -0.0000

Data Index: 771085 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.0897. Min Act: -0.0000

Data Index: 569848 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.0241. Min Act: -0.0000

Data Index: 45189 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.0237. Min Act: -0.0000

Data Index: 1130808 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.0395. Min Act: -0.0000

Data Index: 776692 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 1.6104. Min Range: -1.6104

Max Act: 0.9896. Min Act: -0.0000

Data Index: 317360 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 1.6104. Min Range: -1.6104

Max Act: 0.9976. Min Act: -0.0000

Data Index: 1342499 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 1.6104. Min Range: -1.6104

Max Act: 0.9918. Min Act: -0.0000

Data Index: 1021933 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 1.6104. Min Range: -1.6104

Max Act: 0.9329. Min Act: -0.0000

Data Index: 571058 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 1.6104. Min Range: -1.6104

Max Act: 0.9467. Min Act: -0.0000

Data Index: 814868 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 1.6104. Min Range: -1.6104

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1013729 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 1.6104. Min Range: -1.6104

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1212159 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 1.6104. Min Range: -1.6104

Max Act: 0.9913. Min Act: -0.0000

Data Index: 1142082 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 1.6104. Min Range: -1.6104

Max Act: 0.9690. Min Act: -0.0000

Data Index: 1332056 (C4 (Web Text))

Max Activating Token Index: 194