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

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

Neuron 2425 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: 0.2541. Min Range: -0.2541

Max Act: 0.2299. Min Act: -0.0000

Data Index: 67429 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2380. Min Act: -0.0000

Data Index: 191413 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2541. Min Act: -0.0000

Data Index: 266720 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1053423 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2386. Min Act: -0.0000

Data Index: 1101656 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2179. Min Act: -0.0000

Data Index: 883774 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2239. Min Act: -0.0000

Data Index: 548143 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2127. Min Act: -0.0000

Data Index: 365114 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1286935 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1226347 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2058. Min Act: -0.0000

Data Index: 866801 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2148. Min Act: -0.0000

Data Index: 852018 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1975. Min Act: -0.0000

Data Index: 1373950 (Python Code)

Max Activating Token Index: 1013

Text #13

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2077. Min Act: -0.0000

Data Index: 975578 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2207. Min Act: -0.0000

Data Index: 1072761 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2046. Min Act: -0.0000

Data Index: 1305833 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1999. Min Act: -0.0000

Data Index: 1335697 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2105. Min Act: -0.0000

Data Index: 871363 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2061. Min Act: -0.0000

Data Index: 855357 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1923. Min Act: -0.0000

Data Index: 377305 (C4 (Web Text))

Max Activating Token Index: 464