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

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

Neuron 1416 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.6088. Min Range: -8.6088

Max Act: 8.6088. Min Act: -0.0000

Data Index: 812828 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 8.6088. Min Range: -8.6088

Max Act: 8.2455. Min Act: -0.0000

Data Index: 43534 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 8.6088. Min Range: -8.6088

Max Act: 7.3507. Min Act: -0.0000

Data Index: 6211 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 8.6088. Min Range: -8.6088

Max Act: 6.9788. Min Act: -0.0000

Data Index: 577192 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 8.6088. Min Range: -8.6088

Max Act: 7.0136. Min Act: -0.0000

Data Index: 1206671 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 8.6088. Min Range: -8.6088

Max Act: 6.7980. Min Act: -0.0000

Data Index: 386058 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 8.6088. Min Range: -8.6088

Max Act: 6.7620. Min Act: -0.0000

Data Index: 1492063 (Python Code)

Max Activating Token Index: 1009

Text #7

Max Range: 8.6088. Min Range: -8.6088

Max Act: 6.5240. Min Act: -0.0000

Data Index: 1396045 (Python Code)

Max Activating Token Index: 932

Text #8

Max Range: 8.6088. Min Range: -8.6088

Max Act: 6.3418. Min Act: -0.0000

Data Index: 1561202 (Python Code)

Max Activating Token Index: 239

Text #9

Max Range: 8.6088. Min Range: -8.6088

Max Act: 6.7241. Min Act: -0.0000

Data Index: 1400082 (Python Code)

Max Activating Token Index: 999

Text #10

Max Range: 8.6088. Min Range: -8.6088

Max Act: 6.4689. Min Act: -0.0000

Data Index: 1632155 (Python Code)

Max Activating Token Index: 336

Text #11

Max Range: 8.6088. Min Range: -8.6088

Max Act: 6.4426. Min Act: -0.0000

Data Index: 579206 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 8.6088. Min Range: -8.6088

Max Act: 6.7509. Min Act: -0.0000

Data Index: 747137 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 8.6088. Min Range: -8.6088

Max Act: 6.3014. Min Act: -0.0000

Data Index: 416397 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 8.6088. Min Range: -8.6088

Max Act: 6.2563. Min Act: -0.0000

Data Index: 499544 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 8.6088. Min Range: -8.6088

Max Act: 6.2148. Min Act: -0.0000

Data Index: 1513186 (Python Code)

Max Activating Token Index: 841

Text #16

Max Range: 8.6088. Min Range: -8.6088

Max Act: 6.2114. Min Act: -0.0000

Data Index: 104534 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 8.6088. Min Range: -8.6088

Max Act: 6.1623. Min Act: -0.0000

Data Index: 1512900 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 8.6088. Min Range: -8.6088

Max Act: 6.3460. Min Act: -0.0000

Data Index: 962761 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 8.6088. Min Range: -8.6088

Max Act: 6.1370. Min Act: -0.0000

Data Index: 1635465 (Python Code)

Max Activating Token Index: 637