Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2616 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0338. Min Range: -1.0338

Max Act: 1.0338. Min Act: -0.0001

Data Index: 97208 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.9346. Min Act: -0.0001

Data Index: 1346993 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.8218. Min Act: -0.0001

Data Index: 238438 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.8616. Min Act: -0.0001

Data Index: 365377 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.8310. Min Act: -0.0001

Data Index: 1333080 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.8472. Min Act: -0.0001

Data Index: 494137 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.8453. Min Act: -0.0001

Data Index: 532786 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.7588. Min Act: -0.0001

Data Index: 130271 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.7966. Min Act: -0.0001

Data Index: 1312428 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.7388. Min Act: -0.0001

Data Index: 493359 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.8118. Min Act: -0.0001

Data Index: 675064 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.8071. Min Act: -0.0001

Data Index: 158512 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.7591. Min Act: -0.0001

Data Index: 107603 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.8312. Min Act: -0.0001

Data Index: 82223 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.7528. Min Act: -0.0001

Data Index: 1097706 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.7004. Min Act: -0.0001

Data Index: 721901 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.7633. Min Act: -0.0001

Data Index: 993617 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.7642. Min Act: -0.0001

Data Index: 251733 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.8137. Min Act: -0.0001

Data Index: 853082 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 1.0338. Min Range: -1.0338

Max Act: 0.7900. Min Act: -0.0001

Data Index: 166227 (C4 (Web Text))

Max Activating Token Index: 447