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

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

Neuron 145 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0815. Min Range: -1.0815

Max Act: 1.0815. Min Act: -0.0000

Data Index: 971535 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.8146. Min Act: -0.0000

Data Index: 226159 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.8070. Min Act: -0.0000

Data Index: 1131343 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.7942. Min Act: -0.0000

Data Index: 81694 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.7445. Min Act: -0.0001

Data Index: 96593 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.6904. Min Act: -0.0001

Data Index: 1219202 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.6107. Min Act: -0.0000

Data Index: 1145977 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.6841. Min Act: -0.0000

Data Index: 267308 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.7242. Min Act: 0.0001

Data Index: 774263 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.6278. Min Act: -0.0001

Data Index: 295266 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.6387. Min Act: -0.0000

Data Index: 945549 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.5948. Min Act: -0.0000

Data Index: 572716 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.6042. Min Act: -0.0001

Data Index: 415669 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.5730. Min Act: -0.0000

Data Index: 550274 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.6016. Min Act: -0.0000

Data Index: 864773 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.6107. Min Act: -0.0000

Data Index: 428179 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.6507. Min Act: -0.0000

Data Index: 918348 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.6073. Min Act: -0.0001

Data Index: 316566 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.5817. Min Act: -0.0001

Data Index: 1072962 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.5967. Min Act: -0.0001

Data Index: 934248 (C4 (Web Text))

Max Activating Token Index: 397