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

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

Neuron 4294 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1259. Min Range: -1.1259

Max Act: 1.1259. Min Act: -0.0001

Data Index: 643227 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.7991. Min Act: -0.0001

Data Index: 1335191 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 1.1259. Min Range: -1.1259

Max Act: 1.0032. Min Act: -0.0001

Data Index: 1323913 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.9835. Min Act: -0.0001

Data Index: 18338 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.9705. Min Act: -0.0001

Data Index: 1169602 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.9945. Min Act: -0.0001

Data Index: 366532 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.9032. Min Act: -0.0001

Data Index: 486205 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.9246. Min Act: -0.0001

Data Index: 1306473 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.9146. Min Act: -0.0001

Data Index: 125989 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.9272. Min Act: -0.0001

Data Index: 476302 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.9462. Min Act: -0.0001

Data Index: 540006 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8069. Min Act: -0.0001

Data Index: 242736 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8369. Min Act: -0.0001

Data Index: 719913 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8617. Min Act: -0.0001

Data Index: 1108499 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8708. Min Act: -0.0001

Data Index: 224173 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8317. Min Act: -0.0001

Data Index: 717335 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8377. Min Act: -0.0001

Data Index: 73576 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8010. Min Act: -0.0001

Data Index: 697361 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8241. Min Act: -0.0001

Data Index: 548541 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8230. Min Act: -0.0001

Data Index: 389777 (C4 (Web Text))

Max Activating Token Index: 913