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

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

Neuron 420 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8282. Min Range: -1.8282

Max Act: 1.8282. Min Act: -0.0001

Data Index: 1101912 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 1.8282. Min Range: -1.8282

Max Act: 1.5701. Min Act: -0.0001

Data Index: 767129 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 1.8282. Min Range: -1.8282

Max Act: 1.2802. Min Act: -0.0001

Data Index: 954361 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 1.8282. Min Range: -1.8282

Max Act: 1.3051. Min Act: -0.0001

Data Index: 367851 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 1.8282. Min Range: -1.8282

Max Act: 0.9429. Min Act: -0.0001

Data Index: 1001883 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 1.8282. Min Range: -1.8282

Max Act: 1.0064. Min Act: -0.0001

Data Index: 1137392 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 1.8282. Min Range: -1.8282

Max Act: 0.9747. Min Act: -0.0001

Data Index: 1278858 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 1.8282. Min Range: -1.8282

Max Act: 0.8913. Min Act: -0.0001

Data Index: 532724 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 1.8282. Min Range: -1.8282

Max Act: 0.8619. Min Act: -0.0001

Data Index: 448527 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 1.8282. Min Range: -1.8282

Max Act: 0.8140. Min Act: -0.0001

Data Index: 610579 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 1.8282. Min Range: -1.8282

Max Act: 0.8494. Min Act: -0.0001

Data Index: 678126 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 1.8282. Min Range: -1.8282

Max Act: 0.8168. Min Act: -0.0001

Data Index: 100761 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 1.8282. Min Range: -1.8282

Max Act: 0.7977. Min Act: -0.0001

Data Index: 195585 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 1.8282. Min Range: -1.8282

Max Act: 0.7855. Min Act: -0.0001

Data Index: 665621 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 1.8282. Min Range: -1.8282

Max Act: 0.7510. Min Act: -0.0001

Data Index: 1164762 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 1.8282. Min Range: -1.8282

Max Act: 0.8672. Min Act: -0.0001

Data Index: 905247 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 1.8282. Min Range: -1.8282

Max Act: 0.6939. Min Act: -0.0001

Data Index: 1172640 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 1.8282. Min Range: -1.8282

Max Act: 0.8135. Min Act: -0.0001

Data Index: 896033 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 1.8282. Min Range: -1.8282

Max Act: 0.7985. Min Act: -0.0001

Data Index: 253344 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 1.8282. Min Range: -1.8282

Max Act: 0.7673. Min Act: -0.0001

Data Index: 561221 (C4 (Web Text))

Max Activating Token Index: 367