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

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

Neuron 3106 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: 0.2439. Min Range: -0.2439

Max Act: 0.2439. Min Act: -0.0000

Data Index: 804283 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.2258. Min Act: -0.0000

Data Index: 702966 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.2256. Min Act: -0.0001

Data Index: 376592 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.2239. Min Act: -0.0000

Data Index: 554257 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.2116. Min Act: -0.0000

Data Index: 1332273 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.2198. Min Act: -0.0000

Data Index: 46055 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.2098. Min Act: -0.0001

Data Index: 616649 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.2085. Min Act: -0.0000

Data Index: 1103684 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.2120. Min Act: -0.0001

Data Index: 320281 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.2109. Min Act: -0.0001

Data Index: 511169 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.2069. Min Act: -0.0001

Data Index: 1224230 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1086048 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1239427 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1986. Min Act: -0.0001

Data Index: 733089 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.2029. Min Act: -0.0001

Data Index: 642034 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1943. Min Act: -0.0001

Data Index: 703954 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1952. Min Act: -0.0000

Data Index: 639189 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1984. Min Act: -0.0000

Data Index: 673782 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1915. Min Act: -0.0000

Data Index: 436255 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1895. Min Act: -0.0000

Data Index: 769214 (C4 (Web Text))

Max Activating Token Index: 1006