Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1407 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0561. Min Act: -0.0003

Data Index: 1205621 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0560. Min Act: -0.0004

Data Index: 101522 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1132675 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0485. Min Act: -0.0003

Data Index: 937312 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0491. Min Act: -0.0003

Data Index: 965915 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0479. Min Act: -0.0004

Data Index: 1088199 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0473. Min Act: -0.0003

Data Index: 1139862 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0477. Min Act: -0.0004

Data Index: 1007033 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0468. Min Act: -0.0004

Data Index: 765658 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0444. Min Act: -0.0004

Data Index: 670939 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0470. Min Act: -0.0003

Data Index: 765298 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0458. Min Act: -0.0003

Data Index: 1079719 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0436. Min Act: -0.0003

Data Index: 941739 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0419. Min Act: -0.0004

Data Index: 393905 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0441. Min Act: -0.0003

Data Index: 235534 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0365. Min Act: -0.0004

Data Index: 1180 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0387. Min Act: -0.0003

Data Index: 635200 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0390. Min Act: -0.0003

Data Index: 1084048 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0402. Min Act: -0.0003

Data Index: 412489 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0401. Min Act: -0.0004

Data Index: 464402 (C4 (Web Text))

Max Activating Token Index: 200