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

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

Neuron 954 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: 0.7009. Min Range: -0.7009

Max Act: 0.7009. Min Act: -0.0000

Data Index: 234934 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1358178 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.5944. Min Act: -0.0000

Data Index: 646562 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.4827. Min Act: -0.0000

Data Index: 860720 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.4477. Min Act: -0.0000

Data Index: 296614 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1079165 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.4259. Min Act: 0.0000

Data Index: 790661 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.4400. Min Act: -0.0000

Data Index: 994881 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.4098. Min Act: -0.0000

Data Index: 671106 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.3701. Min Act: -0.0000

Data Index: 996012 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.3999. Min Act: -0.0000

Data Index: 974026 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.3673. Min Act: -0.0000

Data Index: 899957 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1648377 (Python Code)

Max Activating Token Index: 395

Text #13

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.3397. Min Act: -0.0000

Data Index: 194655 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.3525. Min Act: -0.0000

Data Index: 1274235 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.3350. Min Act: -0.0000

Data Index: 100561 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.3170. Min Act: -0.0000

Data Index: 268148 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.3010. Min Act: -0.0000

Data Index: 280227 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.2787. Min Act: -0.0000

Data Index: 1196241 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.7009. Min Range: -0.7009

Max Act: 0.2677. Min Act: -0.0000

Data Index: 541040 (C4 (Web Text))

Max Activating Token Index: 396