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

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

Neuron 2529 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.7383. Min Act: -0.0001

Data Index: 209300 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.7124. Min Act: -0.0001

Data Index: 1652340 (Python Code)

Max Activating Token Index: 999

Text #2

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6053. Min Act: -0.0001

Data Index: 57634 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.5835. Min Act: -0.0001

Data Index: 723939 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.5815. Min Act: -0.0001

Data Index: 1456792 (Python Code)

Max Activating Token Index: 864

Text #5

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.5656. Min Act: -0.0001

Data Index: 193981 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.5396. Min Act: -0.0001

Data Index: 1147428 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6448. Min Act: -0.0001

Data Index: 1433135 (Python Code)

Max Activating Token Index: 564

Text #8

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.5373. Min Act: -0.0000

Data Index: 1388109 (Python Code)

Max Activating Token Index: 122

Text #9

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.4951. Min Act: -0.0001

Data Index: 153588 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6249. Min Act: -0.0000

Data Index: 1536322 (Python Code)

Max Activating Token Index: 418

Text #11

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6127. Min Act: -0.0001

Data Index: 1241623 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.5134. Min Act: -0.0000

Data Index: 1420729 (Python Code)

Max Activating Token Index: 81

Text #13

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.4456. Min Act: -0.0001

Data Index: 283286 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.5465. Min Act: -0.0000

Data Index: 1509881 (Python Code)

Max Activating Token Index: 457

Text #15

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.4424. Min Act: -0.0001

Data Index: 85984 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.4748. Min Act: -0.0001

Data Index: 269146 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.4830. Min Act: -0.0001

Data Index: 1226962 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.4432. Min Act: -0.0001

Data Index: 853313 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.4254. Min Act: -0.0001

Data Index: 551232 (C4 (Web Text))

Max Activating Token Index: 311