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

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

Neuron 3875 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: 0.3147. Min Range: -0.3147

Max Act: 0.3147. Min Act: -0.0000

Data Index: 936334 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.1048. Min Act: -0.0001

Data Index: 325001 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.1569. Min Act: -0.0001

Data Index: 401915 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.1239. Min Act: -0.0001

Data Index: 1393633 (Python Code)

Max Activating Token Index: 447

Text #4

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.1149. Min Act: -0.0001

Data Index: 958162 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.0605. Min Act: -0.0001

Data Index: 772172 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.1064. Min Act: -0.0000

Data Index: 1066880 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1582346 (Python Code)

Max Activating Token Index: 90

Text #8

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.0993. Min Act: -0.0001

Data Index: 1460686 (Python Code)

Max Activating Token Index: 387

Text #9

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.0972. Min Act: -0.0001

Data Index: 1396519 (Python Code)

Max Activating Token Index: 36

Text #10

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1523675 (Python Code)

Max Activating Token Index: 170

Text #11

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.0966. Min Act: -0.0001

Data Index: 47251 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.0935. Min Act: -0.0001

Data Index: 721339 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.0994. Min Act: -0.0001

Data Index: 1317819 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.0982. Min Act: -0.0001

Data Index: 303306 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1189824 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1300548 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.0947. Min Act: -0.0001

Data Index: 1339674 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.0931. Min Act: -0.0001

Data Index: 1457689 (Python Code)

Max Activating Token Index: 895

Text #19

Max Range: 0.3147. Min Range: -0.3147

Max Act: 0.0861. Min Act: -0.0000

Data Index: 92128 (C4 (Web Text))

Max Activating Token Index: 162