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

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

Neuron 1729 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3296. Min Range: -1.3296

Max Act: 1.3296. Min Act: -0.0001

Data Index: 546048 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 1.3296. Min Range: -1.3296

Max Act: 1.1006. Min Act: -0.0001

Data Index: 12281 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 1.3296. Min Range: -1.3296

Max Act: 1.1103. Min Act: -0.0001

Data Index: 1100046 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 1.3296. Min Range: -1.3296

Max Act: 1.0740. Min Act: -0.0001

Data Index: 1114463 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 1.3296. Min Range: -1.3296

Max Act: 1.0470. Min Act: -0.0001

Data Index: 1283246 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 1.3296. Min Range: -1.3296

Max Act: 1.0758. Min Act: -0.0001

Data Index: 980871 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 1.3296. Min Range: -1.3296

Max Act: 1.0057. Min Act: -0.0001

Data Index: 305275 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 1.3296. Min Range: -1.3296

Max Act: 1.0437. Min Act: -0.0001

Data Index: 368987 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.9848. Min Act: -0.0001

Data Index: 596738 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.9985. Min Act: -0.0001

Data Index: 646431 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 1.3296. Min Range: -1.3296

Max Act: 1.0974. Min Act: -0.0001

Data Index: 299350 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.9988. Min Act: -0.0001

Data Index: 504411 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.9787. Min Act: -0.0001

Data Index: 3618 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.9466. Min Act: -0.0001

Data Index: 548581 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.9412. Min Act: -0.0001

Data Index: 1028950 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.9049. Min Act: -0.0001

Data Index: 859767 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 1.3296. Min Range: -1.3296

Max Act: 1.0060. Min Act: -0.0001

Data Index: 44999 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.9890. Min Act: -0.0001

Data Index: 1106501 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 1.3296. Min Range: -1.3296

Max Act: 1.0215. Min Act: -0.0001

Data Index: 354284 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 1.3296. Min Range: -1.3296

Max Act: 1.0134. Min Act: -0.0001

Data Index: 1214539 (C4 (Web Text))

Max Activating Token Index: 549