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

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

Neuron 2947 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: 7.1477. Min Range: -7.1477

Max Act: 7.1477. Min Act: -0.0000

Data Index: 328306 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 7.1477. Min Range: -7.1477

Max Act: 6.3397. Min Act: -0.0000

Data Index: 190242 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 7.1477. Min Range: -7.1477

Max Act: 6.3377. Min Act: -0.0000

Data Index: 821371 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 7.1477. Min Range: -7.1477

Max Act: 5.7369. Min Act: -0.0000

Data Index: 631197 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 7.1477. Min Range: -7.1477

Max Act: 5.9906. Min Act: -0.0000

Data Index: 1269210 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 7.1477. Min Range: -7.1477

Max Act: 5.9467. Min Act: -0.0000

Data Index: 1257317 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 7.1477. Min Range: -7.1477

Max Act: 5.9044. Min Act: -0.0000

Data Index: 694206 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 7.1477. Min Range: -7.1477

Max Act: 5.5226. Min Act: -0.0000

Data Index: 987578 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 7.1477. Min Range: -7.1477

Max Act: 5.7076. Min Act: -0.0000

Data Index: 1115351 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 7.1477. Min Range: -7.1477

Max Act: 5.6123. Min Act: -0.0000

Data Index: 1207476 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 7.1477. Min Range: -7.1477

Max Act: 5.7370. Min Act: -0.0000

Data Index: 794518 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 7.1477. Min Range: -7.1477

Max Act: 5.6804. Min Act: -0.0000

Data Index: 742964 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 7.1477. Min Range: -7.1477

Max Act: 5.8405. Min Act: -0.0000

Data Index: 621251 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 7.1477. Min Range: -7.1477

Max Act: 5.8155. Min Act: -0.0000

Data Index: 1058285 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 7.1477. Min Range: -7.1477

Max Act: 5.6057. Min Act: -0.0000

Data Index: 451983 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 7.1477. Min Range: -7.1477

Max Act: 5.4099. Min Act: -0.0000

Data Index: 1115965 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 7.1477. Min Range: -7.1477

Max Act: 5.7998. Min Act: -0.0000

Data Index: 517455 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 7.1477. Min Range: -7.1477

Max Act: 5.5603. Min Act: -0.0000

Data Index: 348769 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 7.1477. Min Range: -7.1477

Max Act: 5.6867. Min Act: -0.0000

Data Index: 1023051 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 7.1477. Min Range: -7.1477

Max Act: 5.3009. Min Act: -0.0000

Data Index: 1140033 (C4 (Web Text))

Max Activating Token Index: 33