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

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

Neuron 3526 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: 5.4011. Min Range: -5.4011

Max Act: 5.4011. Min Act: -0.0001

Data Index: 973312 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 5.4011. Min Range: -5.4011

Max Act: 3.3434. Min Act: -0.0001

Data Index: 394842 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 5.4011. Min Range: -5.4011

Max Act: 3.3802. Min Act: -0.0001

Data Index: 412558 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 5.4011. Min Range: -5.4011

Max Act: 3.2615. Min Act: -0.0001

Data Index: 262053 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 5.4011. Min Range: -5.4011

Max Act: 3.0118. Min Act: -0.0001

Data Index: 201124 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 5.4011. Min Range: -5.4011

Max Act: 2.6996. Min Act: -0.0001

Data Index: 300480 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 5.4011. Min Range: -5.4011

Max Act: 2.9238. Min Act: -0.0001

Data Index: 888882 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 5.4011. Min Range: -5.4011

Max Act: 2.9147. Min Act: -0.0001

Data Index: 439570 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 5.4011. Min Range: -5.4011

Max Act: 2.9188. Min Act: -0.0001

Data Index: 719645 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 5.4011. Min Range: -5.4011

Max Act: 2.7153. Min Act: -0.0001

Data Index: 392386 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 5.4011. Min Range: -5.4011

Max Act: 2.6289. Min Act: -0.0001

Data Index: 189589 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 5.4011. Min Range: -5.4011

Max Act: 2.5326. Min Act: -0.0001

Data Index: 177108 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 5.4011. Min Range: -5.4011

Max Act: 2.4817. Min Act: -0.0001

Data Index: 1082888 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 5.4011. Min Range: -5.4011

Max Act: 2.4970. Min Act: -0.0001

Data Index: 1155611 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 5.4011. Min Range: -5.4011

Max Act: 2.4789. Min Act: -0.0001

Data Index: 535628 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 5.4011. Min Range: -5.4011

Max Act: 2.3321. Min Act: -0.0001

Data Index: 741842 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 5.4011. Min Range: -5.4011

Max Act: 2.5622. Min Act: -0.0001

Data Index: 1333143 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 5.4011. Min Range: -5.4011

Max Act: 2.4510. Min Act: -0.0001

Data Index: 1141674 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 5.4011. Min Range: -5.4011

Max Act: 2.2814. Min Act: -0.0001

Data Index: 1248494 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 5.4011. Min Range: -5.4011

Max Act: 2.5216. Min Act: -0.0001

Data Index: 542784 (C4 (Web Text))

Max Activating Token Index: 98