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

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

Neuron 4300 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: 0.3810. Min Range: -0.3810

Max Act: 0.3810. Min Act: -0.0000

Data Index: 157771 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.3810. Min Range: -0.3810

Max Act: 0.3107. Min Act: -0.0000

Data Index: 1226852 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.3810. Min Range: -0.3810

Max Act: 0.3109. Min Act: -0.0000

Data Index: 998168 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.3810. Min Range: -0.3810

Max Act: 0.2792. Min Act: -0.0000

Data Index: 368002 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.3810. Min Range: -0.3810

Max Act: 0.2779. Min Act: -0.0000

Data Index: 351029 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.3810. Min Range: -0.3810

Max Act: 0.2530. Min Act: -0.0000

Data Index: 795050 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.3810. Min Range: -0.3810

Max Act: 0.2488. Min Act: -0.0000

Data Index: 843868 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.3810. Min Range: -0.3810

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1291456 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.3810. Min Range: -0.3810

Max Act: 0.2161. Min Act: -0.0000

Data Index: 92855 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.3810. Min Range: -0.3810

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1134699 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 0.3810. Min Range: -0.3810

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1575544 (Python Code)

Max Activating Token Index: 226

Text #11

Max Range: 0.3810. Min Range: -0.3810

Max Act: 0.2201. Min Act: -0.0000

Data Index: 1040470 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.3810. Min Range: -0.3810

Max Act: 0.2117. Min Act: -0.0000

Data Index: 271143 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 0.3810. Min Range: -0.3810

Max Act: 0.1958. Min Act: -0.0000

Data Index: 324673 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.3810. Min Range: -0.3810

Max Act: 0.2073. Min Act: -0.0000

Data Index: 1451801 (Python Code)

Max Activating Token Index: 566

Text #15

Max Range: 0.3810. Min Range: -0.3810

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1230192 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 0.3810. Min Range: -0.3810

Max Act: 0.1952. Min Act: -0.0000

Data Index: 398653 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.3810. Min Range: -0.3810

Max Act: 0.2027. Min Act: -0.0000

Data Index: 1556931 (Python Code)

Max Activating Token Index: 513

Text #18

Max Range: 0.3810. Min Range: -0.3810

Max Act: 0.1993. Min Act: -0.0000

Data Index: 932595 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.3810. Min Range: -0.3810

Max Act: 0.1916. Min Act: -0.0000

Data Index: 658819 (C4 (Web Text))

Max Activating Token Index: 973