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

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

Neuron 2728 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2943. Min Act: -0.0001

Data Index: 1040761 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2590. Min Act: -0.0001

Data Index: 1442994 (Python Code)

Max Activating Token Index: 365

Text #2

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2573. Min Act: -0.0000

Data Index: 116588 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2535. Min Act: -0.0000

Data Index: 898731 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2239. Min Act: -0.0000

Data Index: 61686 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2468. Min Act: -0.0001

Data Index: 599728 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2076. Min Act: -0.0001

Data Index: 228066 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2319. Min Act: -0.0001

Data Index: 1270434 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2113. Min Act: -0.0001

Data Index: 235235 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2155. Min Act: -0.0001

Data Index: 751094 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2151. Min Act: -0.0001

Data Index: 949968 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2206. Min Act: -0.0001

Data Index: 412796 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2192. Min Act: -0.0001

Data Index: 696843 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2089. Min Act: -0.0000

Data Index: 1093749 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2004. Min Act: -0.0001

Data Index: 457078 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2054. Min Act: -0.0001

Data Index: 643113 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.1977. Min Act: -0.0000

Data Index: 230250 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2055. Min Act: -0.0001

Data Index: 963221 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2035. Min Act: -0.0001

Data Index: 139437 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.1988. Min Act: -0.0001

Data Index: 769136 (C4 (Web Text))

Max Activating Token Index: 185