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

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

Neuron 1952 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: 0.9202. Min Range: -0.9202

Max Act: 0.8884. Min Act: -0.0001

Data Index: 17368 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.9202. Min Act: -0.0001

Data Index: 1343119 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.9020. Min Act: -0.0001

Data Index: 347197 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.8012. Min Act: -0.0001

Data Index: 722830 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.8226. Min Act: -0.0001

Data Index: 1188603 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.7901. Min Act: -0.0001

Data Index: 1308372 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.7686. Min Act: -0.0001

Data Index: 107794 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.7166. Min Act: -0.0001

Data Index: 736431 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.8515. Min Act: -0.0001

Data Index: 1082257 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.8486. Min Act: -0.0001

Data Index: 399488 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.8291. Min Act: -0.0001

Data Index: 627186 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.8009. Min Act: -0.0001

Data Index: 845952 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.7538. Min Act: -0.0001

Data Index: 424585 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.5880. Min Act: -0.0001

Data Index: 452586 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.7086. Min Act: -0.0001

Data Index: 548962 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.7037. Min Act: -0.0001

Data Index: 339394 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.6609. Min Act: -0.0001

Data Index: 633794 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.7641. Min Act: -0.0001

Data Index: 402408 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.7314. Min Act: -0.0001

Data Index: 495814 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.8076. Min Act: -0.0001

Data Index: 413845 (C4 (Web Text))

Max Activating Token Index: 343