Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 957 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7942. Min Act: -0.0001

Data Index: 1393782 (Python Code)

Max Activating Token Index: 1006

Text #1

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.8402. Min Act: -0.0001

Data Index: 1558673 (Python Code)

Max Activating Token Index: 842

Text #2

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7600. Min Act: -0.0001

Data Index: 1565007 (Python Code)

Max Activating Token Index: 695

Text #3

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.8271. Min Act: -0.0001

Data Index: 1418271 (Python Code)

Max Activating Token Index: 783

Text #4

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.8182. Min Act: -0.0000

Data Index: 651087 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.8583. Min Act: -0.0001

Data Index: 1476224 (Python Code)

Max Activating Token Index: 1010

Text #6

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7654. Min Act: -0.0001

Data Index: 1603554 (Python Code)

Max Activating Token Index: 892

Text #7

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.9101. Min Act: -0.0001

Data Index: 1628264 (Python Code)

Max Activating Token Index: 959

Text #8

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7774. Min Act: -0.0001

Data Index: 1120530 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7703. Min Act: -0.0001

Data Index: 872524 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7972. Min Act: -0.0001

Data Index: 1414527 (Python Code)

Max Activating Token Index: 998

Text #11

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.6570. Min Act: -0.0001

Data Index: 1496853 (Python Code)

Max Activating Token Index: 692

Text #12

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7193. Min Act: -0.0001

Data Index: 1377759 (Python Code)

Max Activating Token Index: 692

Text #13

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7248. Min Act: -0.0001

Data Index: 1635220 (Python Code)

Max Activating Token Index: 977

Text #14

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.6655. Min Act: -0.0001

Data Index: 1466044 (Python Code)

Max Activating Token Index: 917

Text #15

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.8027. Min Act: -0.0000

Data Index: 1343447 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.7134. Min Act: -0.0001

Data Index: 1562613 (Python Code)

Max Activating Token Index: 856

Text #17

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.6350. Min Act: -0.0001

Data Index: 1543312 (Python Code)

Max Activating Token Index: 584

Text #18

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1402907 (Python Code)

Max Activating Token Index: 820

Text #19

Max Range: 0.9101. Min Range: -0.9101

Max Act: 0.6256. Min Act: -0.0001

Data Index: 1479454 (Python Code)

Max Activating Token Index: 770