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

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

Neuron 2537 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.7092. Min Act: -0.0000

Data Index: 1249276 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.1555. Min Act: -0.0000

Data Index: 102426 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.1009. Min Act: -0.0000

Data Index: 1221102 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.0126. Min Act: -0.0000

Data Index: 795430 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 1.7092. Min Range: -1.7092

Max Act: 0.9038. Min Act: -0.0000

Data Index: 555356 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.0216. Min Act: -0.0000

Data Index: 311486 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.0258. Min Act: -0.0000

Data Index: 147976 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 1.7092. Min Range: -1.7092

Max Act: 0.9515. Min Act: -0.0000

Data Index: 439235 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 1.7092. Min Range: -1.7092

Max Act: 0.9354. Min Act: -0.0000

Data Index: 102968 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 1.7092. Min Range: -1.7092

Max Act: 0.8385. Min Act: -0.0000

Data Index: 1164787 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 1.7092. Min Range: -1.7092

Max Act: 0.9587. Min Act: -0.0000

Data Index: 945662 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 1.7092. Min Range: -1.7092

Max Act: 0.8570. Min Act: -0.0000

Data Index: 639481 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 1.7092. Min Range: -1.7092

Max Act: 0.8708. Min Act: -0.0000

Data Index: 25301 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 1.7092. Min Range: -1.7092

Max Act: 0.8088. Min Act: -0.0000

Data Index: 1321082 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 1.7092. Min Range: -1.7092

Max Act: 0.9448. Min Act: -0.0000

Data Index: 991998 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 1.7092. Min Range: -1.7092

Max Act: 0.9008. Min Act: -0.0000

Data Index: 974486 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 1.7092. Min Range: -1.7092

Max Act: 0.8710. Min Act: -0.0000

Data Index: 834680 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 1.7092. Min Range: -1.7092

Max Act: 0.9494. Min Act: -0.0000

Data Index: 310410 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 1.7092. Min Range: -1.7092

Max Act: 0.9268. Min Act: -0.0000

Data Index: 1296702 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 1.7092. Min Range: -1.7092

Max Act: 0.8647. Min Act: -0.0000

Data Index: 649595 (C4 (Web Text))

Max Activating Token Index: 217