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

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

Neuron 4868 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9088. Min Range: -2.9088

Max Act: 2.7840. Min Act: -0.0000

Data Index: 644525 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 2.9088. Min Range: -2.9088

Max Act: 2.9088. Min Act: -0.0000

Data Index: 612224 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 2.9088. Min Range: -2.9088

Max Act: 2.7581. Min Act: -0.0000

Data Index: 511346 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 2.9088. Min Range: -2.9088

Max Act: 2.6141. Min Act: -0.0000

Data Index: 462167 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 2.9088. Min Range: -2.9088

Max Act: 2.5573. Min Act: -0.0000

Data Index: 379042 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 2.9088. Min Range: -2.9088

Max Act: 2.5496. Min Act: -0.0000

Data Index: 20938 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 2.9088. Min Range: -2.9088

Max Act: 2.5269. Min Act: -0.0000

Data Index: 1032311 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 2.9088. Min Range: -2.9088

Max Act: 2.4433. Min Act: -0.0000

Data Index: 359106 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 2.9088. Min Range: -2.9088

Max Act: 2.3919. Min Act: -0.0000

Data Index: 1078316 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 2.9088. Min Range: -2.9088

Max Act: 2.3954. Min Act: -0.0000

Data Index: 782086 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 2.9088. Min Range: -2.9088

Max Act: 2.5175. Min Act: -0.0000

Data Index: 878671 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 2.9088. Min Range: -2.9088

Max Act: 2.3615. Min Act: -0.0000

Data Index: 103611 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 2.9088. Min Range: -2.9088

Max Act: 2.4939. Min Act: -0.0000

Data Index: 996552 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 2.9088. Min Range: -2.9088

Max Act: 2.3466. Min Act: -0.0000

Data Index: 1139063 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 2.9088. Min Range: -2.9088

Max Act: 2.2249. Min Act: -0.0000

Data Index: 438402 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 2.9088. Min Range: -2.9088

Max Act: 2.3320. Min Act: -0.0000

Data Index: 372990 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 2.9088. Min Range: -2.9088

Max Act: 2.3083. Min Act: -0.0000

Data Index: 36599 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 2.9088. Min Range: -2.9088

Max Act: 2.2648. Min Act: -0.0000

Data Index: 998029 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 2.9088. Min Range: -2.9088

Max Act: 2.0886. Min Act: -0.0000

Data Index: 913428 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 2.9088. Min Range: -2.9088

Max Act: 2.0998. Min Act: -0.0000

Data Index: 225811 (C4 (Web Text))

Max Activating Token Index: 796