Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3968 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.6959. Min Act: -0.0001

Data Index: 284275 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.5059. Min Act: -0.0001

Data Index: 527549 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.4476. Min Act: -0.0001

Data Index: 484559 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.3343. Min Act: -0.0001

Data Index: 1015435 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.3118. Min Act: -0.0001

Data Index: 851601 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.2681. Min Act: -0.0001

Data Index: 327 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.2121. Min Act: -0.0001

Data Index: 571991 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.1485. Min Act: -0.0001

Data Index: 966773 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.2300. Min Act: -0.0001

Data Index: 147574 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.1588. Min Act: -0.0001

Data Index: 224500 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.0996. Min Act: -0.0001

Data Index: 154885 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 1.6959. Min Range: -1.6959

Max Act: 0.8561. Min Act: -0.0001

Data Index: 107782 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.1538. Min Act: -0.0001

Data Index: 323747 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.1142. Min Act: -0.0001

Data Index: 615528 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.3466. Min Act: -0.0001

Data Index: 1157132 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.1011. Min Act: -0.0001

Data Index: 262118 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.0381. Min Act: -0.0001

Data Index: 648835 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.0595. Min Act: -0.0001

Data Index: 367434 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.0747. Min Act: -0.0001

Data Index: 1136225 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 1.6959. Min Range: -1.6959

Max Act: 1.0593. Min Act: -0.0001

Data Index: 756699 (C4 (Web Text))

Max Activating Token Index: 935