Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 830 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0593. Min Act: -0.0003

Data Index: 1058602 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0483. Min Act: -0.0003

Data Index: 192890 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0453. Min Act: -0.0003

Data Index: 1010214 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1147818 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0410. Min Act: -0.0003

Data Index: 113176 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0371. Min Act: -0.0003

Data Index: 1042322 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0419. Min Act: -0.0003

Data Index: 672026 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0425. Min Act: -0.0003

Data Index: 293649 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0396. Min Act: -0.0003

Data Index: 74391 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0387. Min Act: -0.0003

Data Index: 86084 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1132046 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0356. Min Act: -0.0003

Data Index: 1117597 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0461. Min Act: -0.0003

Data Index: 91518 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0370. Min Act: -0.0003

Data Index: 454147 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0352. Min Act: -0.0003

Data Index: 154311 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0385. Min Act: -0.0003

Data Index: 1231344 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0381. Min Act: -0.0003

Data Index: 549648 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0357. Min Act: -0.0003

Data Index: 1006956 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0355. Min Act: -0.0003

Data Index: 1269200 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0381. Min Act: -0.0003

Data Index: 650992 (C4 (Web Text))

Max Activating Token Index: 979