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

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

Neuron 5939 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.8388. Min Act: -0.0000

Data Index: 160280 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.7303. Min Act: -0.0000

Data Index: 595706 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.7440. Min Act: -0.0000

Data Index: 431040 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6373. Min Act: -0.0000

Data Index: 302141 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6596. Min Act: -0.0000

Data Index: 440078 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1180861 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6395. Min Act: -0.0000

Data Index: 542647 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6519. Min Act: -0.0000

Data Index: 698774 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6060. Min Act: -0.0000

Data Index: 1268141 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6448. Min Act: -0.0000

Data Index: 1136382 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6157. Min Act: -0.0000

Data Index: 519277 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6329. Min Act: -0.0000

Data Index: 501200 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6379. Min Act: 0.0000

Data Index: 533105 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6147. Min Act: -0.0000

Data Index: 588610 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6105. Min Act: -0.0000

Data Index: 937052 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6082. Min Act: -0.0000

Data Index: 567633 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.5881. Min Act: -0.0000

Data Index: 497861 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6019. Min Act: -0.0000

Data Index: 1146077 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6198. Min Act: -0.0000

Data Index: 963482 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.5949. Min Act: -0.0000

Data Index: 972984 (C4 (Web Text))

Max Activating Token Index: 344