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

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

Neuron 3907 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3384. Min Range: -0.3384

Max Act: 0.3352. Min Act: -0.0001

Data Index: 236391 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.3384. Min Range: -0.3384

Max Act: 0.3320. Min Act: -0.0001

Data Index: 1310675 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.3384. Min Range: -0.3384

Max Act: 0.3294. Min Act: -0.0001

Data Index: 509664 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.3384. Min Range: -0.3384

Max Act: 0.3145. Min Act: -0.0001

Data Index: 144802 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.3384. Min Range: -0.3384

Max Act: 0.3333. Min Act: -0.0001

Data Index: 445901 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.3384. Min Range: -0.3384

Max Act: 0.3105. Min Act: -0.0001

Data Index: 553839 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.3384. Min Range: -0.3384

Max Act: 0.3313. Min Act: -0.0001

Data Index: 346864 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.3384. Min Range: -0.3384

Max Act: 0.3139. Min Act: -0.0001

Data Index: 1017460 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.3384. Min Range: -0.3384

Max Act: 0.3049. Min Act: -0.0001

Data Index: 351709 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.3384. Min Range: -0.3384

Max Act: 0.3229. Min Act: -0.0001

Data Index: 412851 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.3384. Min Range: -0.3384

Max Act: 0.3200. Min Act: -0.0001

Data Index: 890961 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.3384. Min Range: -0.3384

Max Act: 0.3078. Min Act: -0.0001

Data Index: 414785 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 0.3384. Min Range: -0.3384

Max Act: 0.3258. Min Act: -0.0001

Data Index: 444536 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.3384. Min Range: -0.3384

Max Act: 0.2954. Min Act: -0.0001

Data Index: 14950 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.3384. Min Range: -0.3384

Max Act: 0.3384. Min Act: -0.0001

Data Index: 61336 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 0.3384. Min Range: -0.3384

Max Act: 0.2669. Min Act: -0.0001

Data Index: 159177 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.3384. Min Range: -0.3384

Max Act: 0.3121. Min Act: -0.0001

Data Index: 820535 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.3384. Min Range: -0.3384

Max Act: 0.3207. Min Act: -0.0001

Data Index: 923388 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.3384. Min Range: -0.3384

Max Act: 0.3108. Min Act: -0.0001

Data Index: 40268 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.3384. Min Range: -0.3384

Max Act: 0.2987. Min Act: -0.0001

Data Index: 780247 (C4 (Web Text))

Max Activating Token Index: 59