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

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

Neuron 4433 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: 1.8953. Min Range: -1.8953

Max Act: 1.7164. Min Act: -0.0000

Data Index: 1308270 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.5142. Min Act: -0.0000

Data Index: 572557 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.8953. Min Act: -0.0000

Data Index: 1323274 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.6811. Min Act: -0.0000

Data Index: 1178071 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.5003. Min Act: -0.0000

Data Index: 1049952 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.6323. Min Act: -0.0000

Data Index: 1315364 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.6375. Min Act: -0.0000

Data Index: 416052 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.4010. Min Act: -0.0000

Data Index: 1288474 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.6144. Min Act: -0.0000

Data Index: 1032541 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.5941. Min Act: -0.0000

Data Index: 1131388 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.5766. Min Act: -0.0000

Data Index: 470936 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.5975. Min Act: -0.0000

Data Index: 220257 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.5942. Min Act: -0.0000

Data Index: 234633 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.4008. Min Act: -0.0000

Data Index: 441058 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.4774. Min Act: -0.0000

Data Index: 276943 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.5715. Min Act: -0.0000

Data Index: 384322 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.5540. Min Act: -0.0000

Data Index: 235405 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.6451. Min Act: -0.0000

Data Index: 1035549 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.4591. Min Act: -0.0000

Data Index: 626666 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.5548. Min Act: -0.0000

Data Index: 834817 (C4 (Web Text))

Max Activating Token Index: 184