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

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

Neuron 4848 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.4031. Min Act: -0.0000

Data Index: 1129136 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.4213. Min Act: -0.0000

Data Index: 1296979 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.2599. Min Act: -0.0000

Data Index: 1061047 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.1215. Min Act: -0.0000

Data Index: 578381 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 3.4213. Min Range: -3.4213

Max Act: 2.9633. Min Act: -0.0000

Data Index: 781398 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 3.4213. Min Range: -3.4213

Max Act: 2.9550. Min Act: -0.0000

Data Index: 375244 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 3.4213. Min Range: -3.4213

Max Act: 2.8821. Min Act: -0.0000

Data Index: 204074 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 3.4213. Min Range: -3.4213

Max Act: 2.8791. Min Act: -0.0000

Data Index: 1302032 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 3.4213. Min Range: -3.4213

Max Act: 2.7449. Min Act: -0.0000

Data Index: 609726 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 3.4213. Min Range: -3.4213

Max Act: 3.0032. Min Act: -0.0000

Data Index: 159720 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 3.4213. Min Range: -3.4213

Max Act: 2.9960. Min Act: -0.0000

Data Index: 314789 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 3.4213. Min Range: -3.4213

Max Act: 2.7532. Min Act: -0.0000

Data Index: 788363 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 3.4213. Min Range: -3.4213

Max Act: 2.7454. Min Act: -0.0000

Data Index: 138193 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 3.4213. Min Range: -3.4213

Max Act: 2.6050. Min Act: -0.0000

Data Index: 531034 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 3.4213. Min Range: -3.4213

Max Act: 2.7058. Min Act: -0.0000

Data Index: 752414 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 3.4213. Min Range: -3.4213

Max Act: 2.6118. Min Act: -0.0000

Data Index: 925239 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 3.4213. Min Range: -3.4213

Max Act: 2.6139. Min Act: -0.0000

Data Index: 770097 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 3.4213. Min Range: -3.4213

Max Act: 2.8651. Min Act: -0.0000

Data Index: 352912 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 3.4213. Min Range: -3.4213

Max Act: 2.0798. Min Act: -0.0000

Data Index: 501605 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 3.4213. Min Range: -3.4213

Max Act: 0.9940. Min Act: -0.0000

Data Index: 516709 (C4 (Web Text))

Max Activating Token Index: 669