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

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

Neuron 3547 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: 2.0345. Min Range: -2.0345

Max Act: 2.0345. Min Act: -0.0002

Data Index: 166786 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9978. Min Act: -0.0002

Data Index: 958836 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9136. Min Act: -0.0002

Data Index: 672550 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.8024. Min Act: -0.0002

Data Index: 75756 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.8404. Min Act: -0.0002

Data Index: 893292 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.7999. Min Act: -0.0002

Data Index: 1171114 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.7088. Min Act: -0.0002

Data Index: 38694 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.6752. Min Act: -0.0002

Data Index: 175151 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.7432. Min Act: -0.0002

Data Index: 1251648 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.6806. Min Act: -0.0002

Data Index: 1103488 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.6695. Min Act: -0.0002

Data Index: 617531 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.6463. Min Act: -0.0002

Data Index: 274770 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.6173. Min Act: -0.0002

Data Index: 462495 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.6661. Min Act: -0.0002

Data Index: 803832 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.6863. Min Act: -0.0002

Data Index: 1324289 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.5831. Min Act: -0.0002

Data Index: 263260 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.5701. Min Act: -0.0002

Data Index: 884339 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.5819. Min Act: -0.0002

Data Index: 1050111 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.5516. Min Act: -0.0002

Data Index: 535622 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.5844. Min Act: -0.0002

Data Index: 394360 (C4 (Web Text))

Max Activating Token Index: 60