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

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

Neuron 4946 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2441. Min Range: -1.2441

Max Act: 1.1780. Min Act: -0.0000

Data Index: 557969 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 1.2441. Min Range: -1.2441

Max Act: 1.2441. Min Act: -0.0000

Data Index: 517939 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.9900. Min Act: -0.0000

Data Index: 426317 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.9230. Min Act: -0.0000

Data Index: 84205 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.9665. Min Act: -0.0000

Data Index: 1020384 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.9185. Min Act: -0.0000

Data Index: 1078727 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.8841. Min Act: -0.0000

Data Index: 631962 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.9274. Min Act: -0.0000

Data Index: 1155458 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.9062. Min Act: -0.0000

Data Index: 1188757 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.9041. Min Act: -0.0000

Data Index: 420681 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.8966. Min Act: -0.0000

Data Index: 1106439 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.8216. Min Act: -0.0000

Data Index: 761396 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.8743. Min Act: -0.0000

Data Index: 686703 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.8098. Min Act: -0.0000

Data Index: 163311 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.8107. Min Act: -0.0000

Data Index: 440659 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.8187. Min Act: -0.0000

Data Index: 1333089 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.7783. Min Act: -0.0000

Data Index: 414244 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.8028. Min Act: -0.0000

Data Index: 432825 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.7457. Min Act: -0.0000

Data Index: 789711 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.8140. Min Act: -0.0000

Data Index: 856763 (C4 (Web Text))

Max Activating Token Index: 207