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

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

Neuron 374 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: 1.6330. Min Range: -1.6330

Max Act: 1.6330. Min Act: -0.0001

Data Index: 527804 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.5961. Min Act: -0.0001

Data Index: 1344556 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.5764. Min Act: -0.0001

Data Index: 938831 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.6155. Min Act: -0.0001

Data Index: 421202 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.6049. Min Act: -0.0001

Data Index: 212634 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.5993. Min Act: -0.0001

Data Index: 279365 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.5331. Min Act: -0.0001

Data Index: 903175 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.5377. Min Act: -0.0001

Data Index: 993150 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.4568. Min Act: -0.0001

Data Index: 1192572 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.4362. Min Act: -0.0001

Data Index: 589743 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.3910. Min Act: -0.0001

Data Index: 32261 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.4298. Min Act: -0.0001

Data Index: 959770 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.3373. Min Act: -0.0001

Data Index: 8427 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.2898. Min Act: -0.0001

Data Index: 888299 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.2475. Min Act: -0.0001

Data Index: 545913 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.3208. Min Act: -0.0001

Data Index: 1008474 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.1978. Min Act: -0.0001

Data Index: 914094 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.2732. Min Act: -0.0001

Data Index: 177229 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.2524. Min Act: -0.0001

Data Index: 144487 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.3124. Min Act: -0.0001

Data Index: 184083 (C4 (Web Text))

Max Activating Token Index: 940