Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1351 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1179. Min Range: -0.1179

Max Act: 0.1104. Min Act: -0.0001

Data Index: 413427 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.1179. Min Range: -0.1179

Max Act: 0.1062. Min Act: -0.0001

Data Index: 117606 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 0.1179. Min Range: -0.1179

Max Act: 0.1179. Min Act: -0.0001

Data Index: 1027150 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.1179. Min Range: -0.1179

Max Act: 0.1167. Min Act: -0.0001

Data Index: 1129677 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.1179. Min Range: -0.1179

Max Act: 0.1159. Min Act: -0.0001

Data Index: 149691 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.1179. Min Range: -0.1179

Max Act: 0.1149. Min Act: -0.0001

Data Index: 1542755 (Python Code)

Max Activating Token Index: 616

Text #6

Max Range: 0.1179. Min Range: -0.1179

Max Act: 0.0935. Min Act: -0.0001

Data Index: 402789 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.1179. Min Range: -0.1179

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1391616 (Python Code)

Max Activating Token Index: 354

Text #8

Max Range: 0.1179. Min Range: -0.1179

Max Act: 0.1027. Min Act: -0.0001

Data Index: 1496614 (Python Code)

Max Activating Token Index: 92

Text #9

Max Range: 0.1179. Min Range: -0.1179

Max Act: 0.1065. Min Act: -0.0001

Data Index: 1426187 (Python Code)

Max Activating Token Index: 126

Text #10

Max Range: 0.1179. Min Range: -0.1179

Max Act: 0.1040. Min Act: -0.0001

Data Index: 30340 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.1179. Min Range: -0.1179

Max Act: 0.0941. Min Act: -0.0001

Data Index: 1542239 (Python Code)

Max Activating Token Index: 288

Text #12

Max Range: 0.1179. Min Range: -0.1179

Max Act: 0.0961. Min Act: -0.0001

Data Index: 558050 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.1179. Min Range: -0.1179

Max Act: 0.1036. Min Act: -0.0001

Data Index: 1587379 (Python Code)

Max Activating Token Index: 114

Text #14

Max Range: 0.1179. Min Range: -0.1179

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1478224 (Python Code)

Max Activating Token Index: 129

Text #15

Max Range: 0.1179. Min Range: -0.1179

Max Act: 0.1050. Min Act: -0.0001

Data Index: 1319004 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.1179. Min Range: -0.1179

Max Act: 0.1066. Min Act: -0.0001

Data Index: 790026 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.1179. Min Range: -0.1179

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1473125 (Python Code)

Max Activating Token Index: 577

Text #18

Max Range: 0.1179. Min Range: -0.1179

Max Act: 0.0949. Min Act: -0.0001

Data Index: 1484161 (Python Code)

Max Activating Token Index: 699

Text #19

Max Range: 0.1179. Min Range: -0.1179

Max Act: 0.0805. Min Act: -0.0001

Data Index: 617572 (C4 (Web Text))

Max Activating Token Index: 359