Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1046 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2991. Min Act: -0.0001

Data Index: 1274966 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2495. Min Act: -0.0001

Data Index: 720920 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2528. Min Act: -0.0001

Data Index: 548756 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2521. Min Act: -0.0001

Data Index: 815653 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2458. Min Act: -0.0001

Data Index: 128064 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2369. Min Act: -0.0001

Data Index: 133149 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2163. Min Act: -0.0001

Data Index: 889076 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2246. Min Act: -0.0001

Data Index: 150768 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2214. Min Act: -0.0001

Data Index: 1335677 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2154. Min Act: -0.0001

Data Index: 734864 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2193. Min Act: -0.0001

Data Index: 276500 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2110. Min Act: -0.0001

Data Index: 338090 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2019. Min Act: -0.0001

Data Index: 45677 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2231. Min Act: -0.0001

Data Index: 430363 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2145. Min Act: -0.0001

Data Index: 667992 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2144. Min Act: -0.0001

Data Index: 848173 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.1940. Min Act: -0.0001

Data Index: 326835 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2148. Min Act: -0.0001

Data Index: 116676 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.1973. Min Act: -0.0001

Data Index: 69741 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.1845. Min Act: -0.0001

Data Index: 313205 (C4 (Web Text))

Max Activating Token Index: 793