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

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

Neuron 3732 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.0074. Min Range: -6.0074

Max Act: 5.9860. Min Act: -0.0000

Data Index: 1316472 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 6.0074. Min Range: -6.0074

Max Act: 5.8961. Min Act: -0.0000

Data Index: 822203 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 6.0074. Min Range: -6.0074

Max Act: 5.6817. Min Act: -0.0000

Data Index: 586771 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 6.0074. Min Range: -6.0074

Max Act: 6.0074. Min Act: -0.0000

Data Index: 1263404 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 6.0074. Min Range: -6.0074

Max Act: 5.7746. Min Act: -0.0000

Data Index: 82551 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 6.0074. Min Range: -6.0074

Max Act: 5.4708. Min Act: -0.0000

Data Index: 1193292 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 6.0074. Min Range: -6.0074

Max Act: 5.6456. Min Act: -0.0000

Data Index: 619047 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 6.0074. Min Range: -6.0074

Max Act: 5.4676. Min Act: -0.0000

Data Index: 1094574 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 6.0074. Min Range: -6.0074

Max Act: 5.9450. Min Act: -0.0000

Data Index: 77607 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 6.0074. Min Range: -6.0074

Max Act: 5.4016. Min Act: -0.0000

Data Index: 852069 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 6.0074. Min Range: -6.0074

Max Act: 5.1359. Min Act: -0.0000

Data Index: 371101 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 6.0074. Min Range: -6.0074

Max Act: 5.3318. Min Act: -0.0000

Data Index: 326674 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 6.0074. Min Range: -6.0074

Max Act: 5.0422. Min Act: -0.0000

Data Index: 1306016 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 6.0074. Min Range: -6.0074

Max Act: 4.6163. Min Act: -0.0000

Data Index: 1207028 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 6.0074. Min Range: -6.0074

Max Act: 4.9845. Min Act: -0.0000

Data Index: 31942 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 6.0074. Min Range: -6.0074

Max Act: 5.1487. Min Act: -0.0000

Data Index: 971157 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 6.0074. Min Range: -6.0074

Max Act: 5.1662. Min Act: -0.0000

Data Index: 972545 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 6.0074. Min Range: -6.0074

Max Act: 4.7837. Min Act: -0.0000

Data Index: 1345198 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 6.0074. Min Range: -6.0074

Max Act: 5.0758. Min Act: -0.0000

Data Index: 490857 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 6.0074. Min Range: -6.0074

Max Act: 5.0802. Min Act: -0.0000

Data Index: 112333 (C4 (Web Text))

Max Activating Token Index: 15