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

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

Neuron 3362 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: 0.8085. Min Range: -0.8085

Max Act: 0.8085. Min Act: -0.0001

Data Index: 1117286 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7900. Min Act: -0.0001

Data Index: 209939 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7402. Min Act: -0.0001

Data Index: 77200 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7491. Min Act: -0.0001

Data Index: 898940 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6906. Min Act: -0.0001

Data Index: 479511 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6549. Min Act: -0.0001

Data Index: 1181407 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6703. Min Act: -0.0001

Data Index: 214114 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6714. Min Act: -0.0001

Data Index: 909281 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6716. Min Act: -0.0001

Data Index: 34989 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6447. Min Act: -0.0001

Data Index: 1140485 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6668. Min Act: -0.0001

Data Index: 292582 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6619. Min Act: -0.0001

Data Index: 1329624 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6794. Min Act: -0.0001

Data Index: 1277258 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6543. Min Act: -0.0001

Data Index: 528818 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6542. Min Act: -0.0001

Data Index: 257509 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6273. Min Act: -0.0001

Data Index: 5079 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6435. Min Act: -0.0001

Data Index: 735983 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6166. Min Act: -0.0001

Data Index: 405242 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6323. Min Act: -0.0001

Data Index: 994905 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6334. Min Act: -0.0001

Data Index: 974381 (C4 (Web Text))

Max Activating Token Index: 819