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

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

Neuron 4386 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: 3.7150. Min Range: -3.7150

Max Act: 3.7150. Min Act: -0.0000

Data Index: 16863 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 3.7150. Min Range: -3.7150

Max Act: 2.8392. Min Act: -0.0000

Data Index: 918199 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 3.7150. Min Range: -3.7150

Max Act: 3.1562. Min Act: -0.0000

Data Index: 179118 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 3.7150. Min Range: -3.7150

Max Act: 2.7270. Min Act: -0.0000

Data Index: 708961 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 3.7150. Min Range: -3.7150

Max Act: 2.8431. Min Act: -0.0000

Data Index: 802345 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 3.7150. Min Range: -3.7150

Max Act: 2.8227. Min Act: -0.0000

Data Index: 27897 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 3.7150. Min Range: -3.7150

Max Act: 2.9706. Min Act: -0.0000

Data Index: 932348 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 3.7150. Min Range: -3.7150

Max Act: 2.7776. Min Act: -0.0000

Data Index: 336809 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 3.7150. Min Range: -3.7150

Max Act: 2.7045. Min Act: -0.0000

Data Index: 882106 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 3.7150. Min Range: -3.7150

Max Act: 2.5525. Min Act: -0.0000

Data Index: 53445 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 3.7150. Min Range: -3.7150

Max Act: 2.5350. Min Act: -0.0000

Data Index: 140872 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 3.7150. Min Range: -3.7150

Max Act: 2.7969. Min Act: -0.0000

Data Index: 1081877 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 3.7150. Min Range: -3.7150

Max Act: 2.5221. Min Act: -0.0000

Data Index: 102586 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 3.7150. Min Range: -3.7150

Max Act: 2.5221. Min Act: -0.0000

Data Index: 346323 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 3.7150. Min Range: -3.7150

Max Act: 2.3305. Min Act: -0.0000

Data Index: 951311 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 3.7150. Min Range: -3.7150

Max Act: 2.2904. Min Act: -0.0000

Data Index: 179380 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 3.7150. Min Range: -3.7150

Max Act: 2.2686. Min Act: -0.0000

Data Index: 831085 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 3.7150. Min Range: -3.7150

Max Act: 2.4784. Min Act: -0.0000

Data Index: 319407 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 3.7150. Min Range: -3.7150

Max Act: 2.3348. Min Act: -0.0000

Data Index: 1283902 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 3.7150. Min Range: -3.7150

Max Act: 2.3139. Min Act: -0.0000

Data Index: 1318167 (C4 (Web Text))

Max Activating Token Index: 10