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

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

Neuron 5986 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: 2.0492. Min Range: -2.0492

Max Act: 2.0492. Min Act: -0.0000

Data Index: 1482157 (Python Code)

Max Activating Token Index: 100

Text #1

Max Range: 2.0492. Min Range: -2.0492

Max Act: 1.9980. Min Act: -0.0000

Data Index: 1553247 (Python Code)

Max Activating Token Index: 294

Text #2

Max Range: 2.0492. Min Range: -2.0492

Max Act: 1.8963. Min Act: -0.0000

Data Index: 1500326 (Python Code)

Max Activating Token Index: 389

Text #3

Max Range: 2.0492. Min Range: -2.0492

Max Act: 1.9098. Min Act: -0.0000

Data Index: 1418839 (Python Code)

Max Activating Token Index: 868

Text #4

Max Range: 2.0492. Min Range: -2.0492

Max Act: 1.8461. Min Act: -0.0000

Data Index: 1420882 (Python Code)

Max Activating Token Index: 628

Text #5

Max Range: 2.0492. Min Range: -2.0492

Max Act: 1.7539. Min Act: -0.0000

Data Index: 1634303 (Python Code)

Max Activating Token Index: 985

Text #6

Max Range: 2.0492. Min Range: -2.0492

Max Act: 1.7625. Min Act: -0.0000

Data Index: 219024 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 2.0492. Min Range: -2.0492

Max Act: 1.8518. Min Act: -0.0000

Data Index: 1594959 (Python Code)

Max Activating Token Index: 973

Text #8

Max Range: 2.0492. Min Range: -2.0492

Max Act: 1.6561. Min Act: -0.0000

Data Index: 1564592 (Python Code)

Max Activating Token Index: 237

Text #9

Max Range: 2.0492. Min Range: -2.0492

Max Act: 1.7510. Min Act: -0.0000

Data Index: 1512335 (Python Code)

Max Activating Token Index: 609

Text #10

Max Range: 2.0492. Min Range: -2.0492

Max Act: 1.7437. Min Act: -0.0000

Data Index: 1548211 (Python Code)

Max Activating Token Index: 186

Text #11

Max Range: 2.0492. Min Range: -2.0492

Max Act: 1.8343. Min Act: -0.0000

Data Index: 1443380 (Python Code)

Max Activating Token Index: 694

Text #12

Max Range: 2.0492. Min Range: -2.0492

Max Act: 1.6621. Min Act: -0.0000

Data Index: 1473428 (Python Code)

Max Activating Token Index: 201

Text #13

Max Range: 2.0492. Min Range: -2.0492

Max Act: 1.6582. Min Act: -0.0000

Data Index: 1466819 (Python Code)

Max Activating Token Index: 921

Text #14

Max Range: 2.0492. Min Range: -2.0492

Max Act: 1.7343. Min Act: -0.0000

Data Index: 1507028 (Python Code)

Max Activating Token Index: 401

Text #15

Max Range: 2.0492. Min Range: -2.0492

Max Act: 1.6643. Min Act: -0.0000

Data Index: 1565207 (Python Code)

Max Activating Token Index: 269

Text #16

Max Range: 2.0492. Min Range: -2.0492

Max Act: 1.6526. Min Act: -0.0000

Data Index: 1647958 (Python Code)

Max Activating Token Index: 925

Text #17

Max Range: 2.0492. Min Range: -2.0492

Max Act: 1.6387. Min Act: -0.0000

Data Index: 1486567 (Python Code)

Max Activating Token Index: 1012

Text #18

Max Range: 2.0492. Min Range: -2.0492

Max Act: 1.8273. Min Act: -0.0000

Data Index: 1472661 (Python Code)

Max Activating Token Index: 111

Text #19

Max Range: 2.0492. Min Range: -2.0492

Max Act: 1.6263. Min Act: -0.0000

Data Index: 93205 (C4 (Web Text))

Max Activating Token Index: 849