Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 936 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2469. Min Act: -0.0000

Data Index: 438354 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2276. Min Act: -0.0000

Data Index: 913546 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2336. Min Act: -0.0000

Data Index: 1270391 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2161. Min Act: 0.0000

Data Index: 144974 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2139. Min Act: -0.0000

Data Index: 775723 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1329393 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2107. Min Act: 0.0001

Data Index: 779568 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2164. Min Act: 0.0001

Data Index: 771785 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2242. Min Act: -0.0000

Data Index: 57987 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2063. Min Act: -0.0000

Data Index: 504890 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1301583 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1238957 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1962. Min Act: -0.0000

Data Index: 949962 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1967. Min Act: -0.0000

Data Index: 69293 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1936. Min Act: -0.0000

Data Index: 664308 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2057. Min Act: 0.0000

Data Index: 327202 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1878. Min Act: -0.0000

Data Index: 870872 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1964. Min Act: -0.0000

Data Index: 263343 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2138. Min Act: -0.0000

Data Index: 74961 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1989. Min Act: -0.0000

Data Index: 531411 (C4 (Web Text))

Max Activating Token Index: 291