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

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

Neuron 4028 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2204. Min Range: -4.2204

Max Act: 4.2204. Min Act: -0.0000

Data Index: 521504 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 4.2204. Min Range: -4.2204

Max Act: 3.6816. Min Act: -0.0000

Data Index: 577133 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 4.2204. Min Range: -4.2204

Max Act: 3.8259. Min Act: -0.0000

Data Index: 1276685 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 4.2204. Min Range: -4.2204

Max Act: 3.3748. Min Act: -0.0000

Data Index: 102830 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 4.2204. Min Range: -4.2204

Max Act: 3.2775. Min Act: -0.0000

Data Index: 128305 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 4.2204. Min Range: -4.2204

Max Act: 3.4900. Min Act: -0.0000

Data Index: 1200677 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 4.2204. Min Range: -4.2204

Max Act: 3.4942. Min Act: -0.0000

Data Index: 819074 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 4.2204. Min Range: -4.2204

Max Act: 3.0302. Min Act: -0.0000

Data Index: 286959 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 4.2204. Min Range: -4.2204

Max Act: 2.9041. Min Act: -0.0000

Data Index: 96571 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 4.2204. Min Range: -4.2204

Max Act: 3.3689. Min Act: -0.0000

Data Index: 759877 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 4.2204. Min Range: -4.2204

Max Act: 3.0446. Min Act: -0.0000

Data Index: 696405 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 4.2204. Min Range: -4.2204

Max Act: 3.3175. Min Act: -0.0000

Data Index: 562877 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 4.2204. Min Range: -4.2204

Max Act: 2.7642. Min Act: -0.0000

Data Index: 1201812 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 4.2204. Min Range: -4.2204

Max Act: 2.9120. Min Act: -0.0000

Data Index: 84887 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 4.2204. Min Range: -4.2204

Max Act: 2.8906. Min Act: -0.0000

Data Index: 459676 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 4.2204. Min Range: -4.2204

Max Act: 2.8639. Min Act: -0.0000

Data Index: 950253 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 4.2204. Min Range: -4.2204

Max Act: 2.7548. Min Act: -0.0000

Data Index: 293790 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 4.2204. Min Range: -4.2204

Max Act: 2.8830. Min Act: -0.0000

Data Index: 885744 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 4.2204. Min Range: -4.2204

Max Act: 2.9028. Min Act: -0.0000

Data Index: 335015 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 4.2204. Min Range: -4.2204

Max Act: 2.7150. Min Act: -0.0000

Data Index: 116923 (C4 (Web Text))

Max Activating Token Index: 939