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

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

Neuron 1131 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: 0.9576. Min Range: -0.9576

Max Act: 0.9576. Min Act: -0.0001

Data Index: 1329875 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.7906. Min Act: -0.0001

Data Index: 30193 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.7360. Min Act: -0.0000

Data Index: 543045 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.7120. Min Act: -0.0001

Data Index: 510031 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.6869. Min Act: -0.0001

Data Index: 564106 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.6242. Min Act: -0.0000

Data Index: 343944 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.6748. Min Act: -0.0000

Data Index: 420248 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.6365. Min Act: -0.0000

Data Index: 1145987 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.6415. Min Act: -0.0000

Data Index: 268882 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.5822. Min Act: -0.0000

Data Index: 982167 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.5585. Min Act: -0.0000

Data Index: 158620 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.4762. Min Act: -0.0001

Data Index: 1187410 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.5629. Min Act: -0.0000

Data Index: 402462 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.5581. Min Act: -0.0000

Data Index: 967223 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1009378 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.5486. Min Act: -0.0000

Data Index: 1192638 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.5377. Min Act: -0.0001

Data Index: 1087989 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.5208. Min Act: -0.0000

Data Index: 344772 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.5374. Min Act: -0.0000

Data Index: 314866 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.9576. Min Range: -0.9576

Max Act: 0.5011. Min Act: -0.0000

Data Index: 458690 (C4 (Web Text))

Max Activating Token Index: 417