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

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

Neuron 990 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1348. Min Range: -3.1348

Max Act: 3.1348. Min Act: -0.0001

Data Index: 1146452 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.9466. Min Act: -0.0001

Data Index: 822349 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.7778. Min Act: -0.0001

Data Index: 1340289 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.8411. Min Act: -0.0001

Data Index: 853252 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.7151. Min Act: -0.0001

Data Index: 16406 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.8083. Min Act: -0.0001

Data Index: 596473 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.6889. Min Act: -0.0001

Data Index: 155317 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.5000. Min Act: -0.0001

Data Index: 879156 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.4660. Min Act: -0.0001

Data Index: 1187997 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.4244. Min Act: -0.0001

Data Index: 28790 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.3827. Min Act: -0.0001

Data Index: 712117 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.2613. Min Act: -0.0001

Data Index: 911757 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.6091. Min Act: -0.0001

Data Index: 1203791 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.3132. Min Act: -0.0001

Data Index: 1116416 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.4241. Min Act: -0.0001

Data Index: 276003 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.0787. Min Act: -0.0001

Data Index: 322353 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.2755. Min Act: -0.0001

Data Index: 245725 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.0482. Min Act: -0.0001

Data Index: 536356 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.2730. Min Act: -0.0001

Data Index: 752926 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 3.1348. Min Range: -3.1348

Max Act: 2.2165. Min Act: -0.0001

Data Index: 658866 (C4 (Web Text))

Max Activating Token Index: 7