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

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

Neuron 2735 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.7048. Min Act: -0.0000

Data Index: 1213309 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.6168. Min Act: -0.0001

Data Index: 1412669 (Python Code)

Max Activating Token Index: 1019

Text #2

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.6223. Min Act: -0.0000

Data Index: 1493650 (Python Code)

Max Activating Token Index: 900

Text #3

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.6291. Min Act: -0.0001

Data Index: 1366637 (Python Code)

Max Activating Token Index: 188

Text #4

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.6012. Min Act: -0.0000

Data Index: 1560694 (Python Code)

Max Activating Token Index: 455

Text #5

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.6115. Min Act: -0.0000

Data Index: 1098747 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5977. Min Act: -0.0000

Data Index: 502843 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5903. Min Act: -0.0000

Data Index: 338966 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5329. Min Act: -0.0000

Data Index: 689287 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5650. Min Act: -0.0000

Data Index: 1494061 (Python Code)

Max Activating Token Index: 221

Text #10

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5402. Min Act: -0.0000

Data Index: 1437188 (Python Code)

Max Activating Token Index: 420

Text #11

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5484. Min Act: -0.0000

Data Index: 1356869 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5286. Min Act: -0.0000

Data Index: 514023 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5087. Min Act: -0.0000

Data Index: 75469 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5192. Min Act: -0.0001

Data Index: 1448290 (Python Code)

Max Activating Token Index: 363

Text #15

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1633573 (Python Code)

Max Activating Token Index: 361

Text #16

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5223. Min Act: -0.0000

Data Index: 1430882 (Python Code)

Max Activating Token Index: 982

Text #17

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5298. Min Act: -0.0000

Data Index: 1224088 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5144. Min Act: -0.0000

Data Index: 1105933 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5031. Min Act: -0.0001

Data Index: 561954 (C4 (Web Text))

Max Activating Token Index: 778