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

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

Neuron 5336 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: 2.5164. Min Range: -2.5164

Max Act: 2.5164. Min Act: -0.0000

Data Index: 1550835 (Python Code)

Max Activating Token Index: 235

Text #1

Max Range: 2.5164. Min Range: -2.5164

Max Act: 2.3540. Min Act: -0.0000

Data Index: 703519 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 2.5164. Min Range: -2.5164

Max Act: 2.1141. Min Act: -0.0000

Data Index: 1209580 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 2.5164. Min Range: -2.5164

Max Act: 2.3977. Min Act: -0.0000

Data Index: 1578143 (Python Code)

Max Activating Token Index: 157

Text #4

Max Range: 2.5164. Min Range: -2.5164

Max Act: 2.1876. Min Act: -0.0000

Data Index: 191933 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 2.5164. Min Range: -2.5164

Max Act: 2.1307. Min Act: -0.0000

Data Index: 32814 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 2.5164. Min Range: -2.5164

Max Act: 1.9527. Min Act: -0.0000

Data Index: 1481184 (Python Code)

Max Activating Token Index: 1000

Text #7

Max Range: 2.5164. Min Range: -2.5164

Max Act: 1.9300. Min Act: -0.0000

Data Index: 585264 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 2.5164. Min Range: -2.5164

Max Act: 2.0262. Min Act: -0.0000

Data Index: 885342 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 2.5164. Min Range: -2.5164

Max Act: 1.9151. Min Act: -0.0000

Data Index: 1123965 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 2.5164. Min Range: -2.5164

Max Act: 1.8097. Min Act: -0.0000

Data Index: 867664 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 2.5164. Min Range: -2.5164

Max Act: 1.8049. Min Act: -0.0000

Data Index: 313792 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 2.5164. Min Range: -2.5164

Max Act: 1.8033. Min Act: -0.0000

Data Index: 971725 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 2.5164. Min Range: -2.5164

Max Act: 1.9943. Min Act: -0.0000

Data Index: 266742 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 2.5164. Min Range: -2.5164

Max Act: 1.7873. Min Act: -0.0000

Data Index: 266623 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 2.5164. Min Range: -2.5164

Max Act: 1.8717. Min Act: -0.0000

Data Index: 186586 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 2.5164. Min Range: -2.5164

Max Act: 1.8161. Min Act: -0.0000

Data Index: 1508965 (Python Code)

Max Activating Token Index: 715

Text #17

Max Range: 2.5164. Min Range: -2.5164

Max Act: 1.8194. Min Act: -0.0000

Data Index: 811738 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 2.5164. Min Range: -2.5164

Max Act: 1.5145. Min Act: -0.0000

Data Index: 1411347 (Python Code)

Max Activating Token Index: 854

Text #19

Max Range: 2.5164. Min Range: -2.5164

Max Act: 1.6985. Min Act: -0.0000

Data Index: 971112 (C4 (Web Text))

Max Activating Token Index: 976