Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 932 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3043. Min Range: -1.3043

Max Act: 1.3043. Min Act: -0.0000

Data Index: 852367 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 1.3043. Min Range: -1.3043

Max Act: 0.8600. Min Act: -0.0000

Data Index: 492307 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 1.3043. Min Range: -1.3043

Max Act: 0.7532. Min Act: -0.0000

Data Index: 251558 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 1.3043. Min Range: -1.3043

Max Act: 0.6323. Min Act: -0.0000

Data Index: 142870 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 1.3043. Min Range: -1.3043

Max Act: 0.6230. Min Act: -0.0000

Data Index: 1306574 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 1.3043. Min Range: -1.3043

Max Act: 0.6640. Min Act: -0.0000

Data Index: 342232 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 1.3043. Min Range: -1.3043

Max Act: 0.5702. Min Act: -0.0000

Data Index: 1059423 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 1.3043. Min Range: -1.3043

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1168559 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 1.3043. Min Range: -1.3043

Max Act: 0.5519. Min Act: -0.0000

Data Index: 825264 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 1.3043. Min Range: -1.3043

Max Act: 0.5475. Min Act: -0.0000

Data Index: 124020 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 1.3043. Min Range: -1.3043

Max Act: 0.5486. Min Act: -0.0000

Data Index: 945394 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 1.3043. Min Range: -1.3043

Max Act: 0.5482. Min Act: -0.0000

Data Index: 532276 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 1.3043. Min Range: -1.3043

Max Act: 0.5241. Min Act: 0.0000

Data Index: 255649 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 1.3043. Min Range: -1.3043

Max Act: 0.5764. Min Act: -0.0000

Data Index: 509914 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 1.3043. Min Range: -1.3043

Max Act: 0.5289. Min Act: -0.0000

Data Index: 295310 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 1.3043. Min Range: -1.3043

Max Act: 0.5230. Min Act: -0.0000

Data Index: 607458 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 1.3043. Min Range: -1.3043

Max Act: 0.5163. Min Act: -0.0000

Data Index: 352453 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 1.3043. Min Range: -1.3043

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1557681 (Python Code)

Max Activating Token Index: 317

Text #18

Max Range: 1.3043. Min Range: -1.3043

Max Act: 0.5117. Min Act: -0.0000

Data Index: 942991 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 1.3043. Min Range: -1.3043

Max Act: 0.5319. Min Act: -0.0000

Data Index: 941769 (C4 (Web Text))

Max Activating Token Index: 291