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

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

Neuron 1171 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.6150. Min Act: -0.0001

Data Index: 394019 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.6026. Min Act: -0.0001

Data Index: 433898 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5589. Min Act: -0.0001

Data Index: 610563 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5793. Min Act: -0.0001

Data Index: 5663 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5755. Min Act: -0.0001

Data Index: 298305 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5865. Min Act: -0.0001

Data Index: 319960 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5661. Min Act: -0.0001

Data Index: 683891 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5464. Min Act: -0.0001

Data Index: 1449259 (Python Code)

Max Activating Token Index: 409

Text #8

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5521. Min Act: -0.0001

Data Index: 1033689 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5404. Min Act: -0.0001

Data Index: 353941 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5443. Min Act: -0.0001

Data Index: 1207068 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5405. Min Act: -0.0001

Data Index: 1302787 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.4852. Min Act: -0.0001

Data Index: 864675 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5345. Min Act: -0.0001

Data Index: 411198 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5326. Min Act: -0.0001

Data Index: 883562 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5344. Min Act: -0.0001

Data Index: 252977 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5690. Min Act: -0.0001

Data Index: 702458 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5121. Min Act: -0.0001

Data Index: 88224 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5465. Min Act: -0.0001

Data Index: 571950 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 0.6150. Min Range: -0.6150

Max Act: 0.5120. Min Act: -0.0001

Data Index: 806566 (C4 (Web Text))

Max Activating Token Index: 914