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

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

Neuron 5377 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.8911. Min Act: -0.0000

Data Index: 436280 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.5957. Min Act: -0.0000

Data Index: 536073 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.3214. Min Act: -0.0000

Data Index: 193925 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.2364. Min Act: -0.0000

Data Index: 1039300 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.0881. Min Act: -0.0000

Data Index: 943174 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.1436. Min Act: -0.0000

Data Index: 841201 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.1472. Min Act: -0.0000

Data Index: 387149 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.0869. Min Act: -0.0000

Data Index: 313977 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.0720. Min Act: -0.0000

Data Index: 307043 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 1.8911. Min Range: -1.8911

Max Act: 0.9896. Min Act: -0.0000

Data Index: 143389 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.0447. Min Act: -0.0000

Data Index: 127611 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 1.8911. Min Range: -1.8911

Max Act: 0.9937. Min Act: 0.0000

Data Index: 555767 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 1.8911. Min Range: -1.8911

Max Act: 0.9947. Min Act: -0.0000

Data Index: 654333 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 1.8911. Min Range: -1.8911

Max Act: 0.9273. Min Act: 0.0000

Data Index: 987287 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 1.8911. Min Range: -1.8911

Max Act: 0.9928. Min Act: -0.0000

Data Index: 111028 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 1.8911. Min Range: -1.8911

Max Act: 1.0362. Min Act: -0.0000

Data Index: 21275 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 1.8911. Min Range: -1.8911

Max Act: 0.8968. Min Act: -0.0000

Data Index: 925359 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 1.8911. Min Range: -1.8911

Max Act: 0.9523. Min Act: -0.0000

Data Index: 441237 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 1.8911. Min Range: -1.8911

Max Act: 0.9514. Min Act: -0.0000

Data Index: 412751 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 1.8911. Min Range: -1.8911

Max Act: 0.8939. Min Act: -0.0000

Data Index: 639546 (C4 (Web Text))

Max Activating Token Index: 855