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

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

Neuron 408 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: 1.7825. Min Range: -1.7825

Max Act: 1.7488. Min Act: -0.0002

Data Index: 1512171 (Python Code)

Max Activating Token Index: 673

Text #1

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.7825. Min Act: -0.0002

Data Index: 1583087 (Python Code)

Max Activating Token Index: 408

Text #2

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.7559. Min Act: -0.0002

Data Index: 1548707 (Python Code)

Max Activating Token Index: 491

Text #3

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.7042. Min Act: -0.0002

Data Index: 1647516 (Python Code)

Max Activating Token Index: 698

Text #4

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.6886. Min Act: -0.0002

Data Index: 1636936 (Python Code)

Max Activating Token Index: 176

Text #5

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.7235. Min Act: -0.0002

Data Index: 1525983 (Python Code)

Max Activating Token Index: 794

Text #6

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.5830. Min Act: -0.0002

Data Index: 1483175 (Python Code)

Max Activating Token Index: 929

Text #7

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.5824. Min Act: -0.0002

Data Index: 1419397 (Python Code)

Max Activating Token Index: 486

Text #8

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.5622. Min Act: -0.0002

Data Index: 1454069 (Python Code)

Max Activating Token Index: 682

Text #9

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.5963. Min Act: -0.0002

Data Index: 1408667 (Python Code)

Max Activating Token Index: 887

Text #10

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.5470. Min Act: -0.0002

Data Index: 1558691 (Python Code)

Max Activating Token Index: 612

Text #11

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.5500. Min Act: -0.0002

Data Index: 1414496 (Python Code)

Max Activating Token Index: 722

Text #12

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.5905. Min Act: -0.0002

Data Index: 1465284 (Python Code)

Max Activating Token Index: 268

Text #13

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.5146. Min Act: -0.0002

Data Index: 1445245 (Python Code)

Max Activating Token Index: 162

Text #14

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.5377. Min Act: -0.0002

Data Index: 1441386 (Python Code)

Max Activating Token Index: 673

Text #15

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.5530. Min Act: -0.0002

Data Index: 1385315 (Python Code)

Max Activating Token Index: 1021

Text #16

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.5984. Min Act: -0.0002

Data Index: 1552735 (Python Code)

Max Activating Token Index: 716

Text #17

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.5189. Min Act: -0.0002

Data Index: 1515001 (Python Code)

Max Activating Token Index: 528

Text #18

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.5133. Min Act: -0.0002

Data Index: 1600599 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.5608. Min Act: -0.0002

Data Index: 1476490 (Python Code)

Max Activating Token Index: 550