Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5453 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.0294. Min Range: -5.0294

Max Act: 5.0294. Min Act: -0.0000

Data Index: 755394 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 5.0294. Min Range: -5.0294

Max Act: 4.6355. Min Act: -0.0000

Data Index: 20666 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 5.0294. Min Range: -5.0294

Max Act: 3.7847. Min Act: -0.0000

Data Index: 434730 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 5.0294. Min Range: -5.0294

Max Act: 3.5281. Min Act: -0.0000

Data Index: 69935 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 5.0294. Min Range: -5.0294

Max Act: 3.6402. Min Act: -0.0000

Data Index: 1260947 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 5.0294. Min Range: -5.0294

Max Act: 3.5507. Min Act: -0.0000

Data Index: 1197833 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 5.0294. Min Range: -5.0294

Max Act: 3.0528. Min Act: -0.0000

Data Index: 1113111 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 5.0294. Min Range: -5.0294

Max Act: 3.3074. Min Act: -0.0000

Data Index: 1329119 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 5.0294. Min Range: -5.0294

Max Act: 3.3135. Min Act: -0.0000

Data Index: 618835 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 5.0294. Min Range: -5.0294

Max Act: 3.3048. Min Act: -0.0000

Data Index: 819566 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 5.0294. Min Range: -5.0294

Max Act: 2.8533. Min Act: -0.0000

Data Index: 720 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 5.0294. Min Range: -5.0294

Max Act: 3.3169. Min Act: -0.0000

Data Index: 262765 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 5.0294. Min Range: -5.0294

Max Act: 3.2100. Min Act: -0.0000

Data Index: 841416 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 5.0294. Min Range: -5.0294

Max Act: 3.2037. Min Act: -0.0000

Data Index: 937934 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 5.0294. Min Range: -5.0294

Max Act: 3.2195. Min Act: -0.0000

Data Index: 1327650 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 5.0294. Min Range: -5.0294

Max Act: 2.9050. Min Act: -0.0000

Data Index: 119417 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 5.0294. Min Range: -5.0294

Max Act: 3.2195. Min Act: -0.0000

Data Index: 266461 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 5.0294. Min Range: -5.0294

Max Act: 3.3668. Min Act: -0.0000

Data Index: 937411 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 5.0294. Min Range: -5.0294

Max Act: 2.8046. Min Act: -0.0000

Data Index: 344705 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 5.0294. Min Range: -5.0294

Max Act: 3.1730. Min Act: -0.0000

Data Index: 175022 (C4 (Web Text))

Max Activating Token Index: 567