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

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

Neuron 2016 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.4342. Min Act: -0.0001

Data Index: 1322195 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.4345. Min Act: -0.0001

Data Index: 1117 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3699. Min Act: -0.0001

Data Index: 1196347 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3187. Min Act: -0.0001

Data Index: 874996 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3197. Min Act: -0.0001

Data Index: 385151 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3433. Min Act: -0.0001

Data Index: 898676 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3090. Min Act: -0.0001

Data Index: 1168525 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3061. Min Act: -0.0001

Data Index: 242750 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.2643. Min Act: -0.0001

Data Index: 780134 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3018. Min Act: -0.0001

Data Index: 862843 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.2845. Min Act: -0.0001

Data Index: 289103 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.2797. Min Act: -0.0001

Data Index: 219462 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3281. Min Act: -0.0001

Data Index: 1012933 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3230. Min Act: -0.0001

Data Index: 308084 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.2949. Min Act: -0.0001

Data Index: 1238858 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.3021. Min Act: -0.0001

Data Index: 46675 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.2629. Min Act: -0.0001

Data Index: 836322 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.2399. Min Act: -0.0001

Data Index: 830412 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.2565. Min Act: -0.0001

Data Index: 273237 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.4345. Min Range: -0.4345

Max Act: 0.2786. Min Act: -0.0001

Data Index: 1183136 (C4 (Web Text))

Max Activating Token Index: 498