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

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

Neuron 3427 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.8476. Min Act: -0.0000

Data Index: 140344 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.7522. Min Act: -0.0000

Data Index: 1207573 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1171127 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.7216. Min Act: -0.0000

Data Index: 833130 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.7493. Min Act: -0.0000

Data Index: 623564 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.7250. Min Act: -0.0000

Data Index: 1162291 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.7163. Min Act: -0.0000

Data Index: 394287 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.7374. Min Act: -0.0000

Data Index: 254841 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.7206. Min Act: -0.0000

Data Index: 367274 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.7021. Min Act: -0.0000

Data Index: 25806 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.7138. Min Act: -0.0000

Data Index: 1278065 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.7104. Min Act: -0.0000

Data Index: 988470 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6967. Min Act: -0.0000

Data Index: 117560 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6572. Min Act: -0.0000

Data Index: 991797 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6959. Min Act: -0.0000

Data Index: 24330 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6784. Min Act: -0.0000

Data Index: 392252 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6699. Min Act: -0.0000

Data Index: 1040633 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6134. Min Act: -0.0000

Data Index: 698726 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6129. Min Act: -0.0000

Data Index: 561987 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.8476. Min Range: -0.8476

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1055622 (C4 (Web Text))

Max Activating Token Index: 966