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

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

Neuron 2071 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: 0.9144. Min Range: -0.9144

Max Act: 0.9144. Min Act: -0.0002

Data Index: 505665 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.9030. Min Act: -0.0002

Data Index: 450755 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.8464. Min Act: -0.0002

Data Index: 1181082 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.8138. Min Act: -0.0002

Data Index: 112252 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.8330. Min Act: -0.0002

Data Index: 1277602 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.7981. Min Act: -0.0002

Data Index: 1315410 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.8003. Min Act: -0.0002

Data Index: 554287 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.7882. Min Act: -0.0002

Data Index: 999704 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.7769. Min Act: -0.0002

Data Index: 788857 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.7869. Min Act: -0.0002

Data Index: 814001 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.7520. Min Act: -0.0002

Data Index: 282192 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.7601. Min Act: -0.0002

Data Index: 67661 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.7504. Min Act: -0.0002

Data Index: 66026 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.7370. Min Act: -0.0002

Data Index: 1153911 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.7555. Min Act: -0.0002

Data Index: 1350741 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.7510. Min Act: -0.0002

Data Index: 260881 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.7390. Min Act: -0.0002

Data Index: 775809 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.7281. Min Act: -0.0002

Data Index: 787085 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.7305. Min Act: -0.0002

Data Index: 1053342 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.9144. Min Range: -0.9144

Max Act: 0.7303. Min Act: -0.0002

Data Index: 1174559 (C4 (Web Text))

Max Activating Token Index: 609