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

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

Neuron 3143 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1171717 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.4952. Min Act: -0.0000

Data Index: 369806 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1157770 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3833. Min Act: 0.0000

Data Index: 910920 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3705. Min Act: -0.0000

Data Index: 220609 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1272551 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3509. Min Act: -0.0000

Data Index: 563961 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3476. Min Act: 0.0000

Data Index: 895336 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3436. Min Act: -0.0000

Data Index: 740008 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3425. Min Act: 0.0001

Data Index: 1106906 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3503. Min Act: -0.0000

Data Index: 4384 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3460. Min Act: -0.0000

Data Index: 158654 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3626. Min Act: -0.0000

Data Index: 114504 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3201. Min Act: -0.0000

Data Index: 64064 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3181. Min Act: -0.0000

Data Index: 862613 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3156. Min Act: -0.0000

Data Index: 1262277 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3107. Min Act: 0.0000

Data Index: 370574 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.2999. Min Act: -0.0000

Data Index: 729302 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3077. Min Act: -0.0000

Data Index: 858705 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.3037. Min Act: -0.0000

Data Index: 550010 (C4 (Web Text))

Max Activating Token Index: 576