Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5097 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.8457. Min Act: -0.0000

Data Index: 944866 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.8274. Min Act: -0.0000

Data Index: 296262 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7647. Min Act: -0.0000

Data Index: 137667 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7705. Min Act: -0.0000

Data Index: 417077 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7319. Min Act: -0.0000

Data Index: 944006 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1299489 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7223. Min Act: -0.0000

Data Index: 450178 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7236. Min Act: -0.0000

Data Index: 6242 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6529. Min Act: -0.0000

Data Index: 109707 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6703. Min Act: -0.0000

Data Index: 83580 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7054. Min Act: -0.0000

Data Index: 358981 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6860. Min Act: -0.0000

Data Index: 649684 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7021. Min Act: -0.0000

Data Index: 533569 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1040971 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1183602 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6917. Min Act: -0.0000

Data Index: 586851 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6612. Min Act: -0.0000

Data Index: 1068545 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7285. Min Act: -0.0000

Data Index: 706225 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6729. Min Act: -0.0000

Data Index: 1229454 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6510. Min Act: -0.0000

Data Index: 721512 (C4 (Web Text))

Max Activating Token Index: 957