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

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

Neuron 4046 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.9780. Min Act: -0.0001

Data Index: 471154 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.9425. Min Act: -0.0001

Data Index: 1166049 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.8287. Min Act: -0.0002

Data Index: 1097186 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.8594. Min Act: -0.0001

Data Index: 925503 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.8234. Min Act: -0.0002

Data Index: 840415 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.8423. Min Act: -0.0001

Data Index: 1308556 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.8016. Min Act: -0.0002

Data Index: 529818 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.8165. Min Act: -0.0002

Data Index: 429651 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.8464. Min Act: -0.0002

Data Index: 970222 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.8773. Min Act: -0.0001

Data Index: 1080719 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7616. Min Act: -0.0002

Data Index: 441808 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7860. Min Act: -0.0001

Data Index: 757489 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.8800. Min Act: -0.0001

Data Index: 876651 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.8605. Min Act: -0.0002

Data Index: 234977 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7626. Min Act: -0.0002

Data Index: 502281 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7235. Min Act: -0.0002

Data Index: 870069 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7947. Min Act: -0.0002

Data Index: 527242 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7861. Min Act: -0.0001

Data Index: 976686 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.8036. Min Act: -0.0002

Data Index: 563867 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7762. Min Act: -0.0002

Data Index: 1122356 (C4 (Web Text))

Max Activating Token Index: 34