Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 169 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3755. Min Act: -0.0000

Data Index: 624026 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3335. Min Act: -0.0000

Data Index: 377000 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3099. Min Act: -0.0000

Data Index: 276607 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3073. Min Act: -0.0000

Data Index: 901957 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3084. Min Act: -0.0000

Data Index: 1285221 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.3038. Min Act: -0.0000

Data Index: 1217241 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2838. Min Act: -0.0000

Data Index: 749598 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2732. Min Act: -0.0000

Data Index: 306841 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2721. Min Act: -0.0000

Data Index: 519676 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2650. Min Act: -0.0000

Data Index: 747617 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1329454 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2292. Min Act: -0.0000

Data Index: 389918 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2326. Min Act: -0.0001

Data Index: 1345283 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2284. Min Act: -0.0000

Data Index: 50061 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1105845 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2299. Min Act: -0.0001

Data Index: 343017 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2246. Min Act: -0.0000

Data Index: 990621 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2163. Min Act: -0.0000

Data Index: 731005 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1213176 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.3755. Min Range: -0.3755

Max Act: 0.2162. Min Act: -0.0001

Data Index: 552157 (C4 (Web Text))

Max Activating Token Index: 108