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

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

Neuron 694 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2939. Min Act: -0.0001

Data Index: 1242328 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2430. Min Act: -0.0001

Data Index: 43555 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2128. Min Act: -0.0001

Data Index: 741776 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2183. Min Act: -0.0001

Data Index: 902321 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2310. Min Act: -0.0001

Data Index: 414406 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2245. Min Act: -0.0001

Data Index: 1066550 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2231. Min Act: -0.0001

Data Index: 1107026 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.1991. Min Act: -0.0001

Data Index: 706446 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2074. Min Act: -0.0001

Data Index: 116639 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2129. Min Act: -0.0001

Data Index: 1028805 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.1968. Min Act: -0.0001

Data Index: 485358 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2035. Min Act: -0.0001

Data Index: 853178 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2059. Min Act: -0.0001

Data Index: 763747 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2049. Min Act: -0.0001

Data Index: 522825 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.1977. Min Act: -0.0001

Data Index: 310233 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.1965. Min Act: -0.0001

Data Index: 308445 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.1906. Min Act: -0.0001

Data Index: 505894 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.1941. Min Act: -0.0001

Data Index: 1374606 (Python Code)

Max Activating Token Index: 650

Text #18

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.2093. Min Act: -0.0001

Data Index: 833414 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.2939. Min Range: -0.2939

Max Act: 0.1874. Min Act: -0.0001

Data Index: 999031 (C4 (Web Text))

Max Activating Token Index: 725