Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4078 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3554. Min Act: -0.0000

Data Index: 540259 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3569. Min Act: -0.0001

Data Index: 841820 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3459. Min Act: -0.0000

Data Index: 490830 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3014. Min Act: -0.0000

Data Index: 612795 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2734. Min Act: -0.0000

Data Index: 615609 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2899. Min Act: -0.0001

Data Index: 336347 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1027401 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2760. Min Act: -0.0001

Data Index: 774584 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2660. Min Act: -0.0001

Data Index: 1101492 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2562. Min Act: -0.0001

Data Index: 239373 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2314. Min Act: -0.0001

Data Index: 1285449 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2365. Min Act: -0.0000

Data Index: 214281 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2352. Min Act: 0.0000

Data Index: 514057 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2229. Min Act: -0.0001

Data Index: 1190075 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2227. Min Act: -0.0000

Data Index: 501786 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2215. Min Act: -0.0000

Data Index: 901973 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2176. Min Act: -0.0000

Data Index: 615719 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1331961 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2025. Min Act: -0.0000

Data Index: 964194 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2048. Min Act: -0.0001

Data Index: 61238 (C4 (Web Text))

Max Activating Token Index: 702