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

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

Neuron 151 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: 0.3908. Min Range: -0.3908

Max Act: 0.3908. Min Act: -0.0001

Data Index: 124065 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2743. Min Act: -0.0001

Data Index: 114221 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2587. Min Act: -0.0001

Data Index: 175484 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2437. Min Act: -0.0001

Data Index: 679403 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2339. Min Act: -0.0001

Data Index: 443205 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2571. Min Act: -0.0001

Data Index: 659446 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2461. Min Act: -0.0001

Data Index: 240831 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2462. Min Act: -0.0001

Data Index: 33260 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2530. Min Act: -0.0001

Data Index: 1211578 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2441. Min Act: -0.0001

Data Index: 864601 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2255. Min Act: -0.0001

Data Index: 373159 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2304. Min Act: -0.0001

Data Index: 171851 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2261. Min Act: -0.0001

Data Index: 49291 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2313. Min Act: -0.0001

Data Index: 144093 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2201. Min Act: -0.0000

Data Index: 698548 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2263. Min Act: -0.0001

Data Index: 505732 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2033. Min Act: -0.0001

Data Index: 260556 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2180. Min Act: -0.0001

Data Index: 75626 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2241. Min Act: -0.0001

Data Index: 265885 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2169. Min Act: -0.0001

Data Index: 40505 (C4 (Web Text))

Max Activating Token Index: 648