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

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

Neuron 1145 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9586. Min Range: -1.9586

Max Act: 1.9586. Min Act: -0.0000

Data Index: 533800 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 1.9586. Min Range: -1.9586

Max Act: 1.8527. Min Act: -0.0001

Data Index: 1353371 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 1.9586. Min Range: -1.9586

Max Act: 1.8136. Min Act: -0.0001

Data Index: 1020448 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 1.9586. Min Range: -1.9586

Max Act: 1.7190. Min Act: -0.0001

Data Index: 1253125 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 1.9586. Min Range: -1.9586

Max Act: 1.7149. Min Act: -0.0000

Data Index: 1107476 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 1.9586. Min Range: -1.9586

Max Act: 1.7713. Min Act: -0.0001

Data Index: 135668 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 1.9586. Min Range: -1.9586

Max Act: 1.6799. Min Act: -0.0000

Data Index: 196104 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 1.9586. Min Range: -1.9586

Max Act: 1.6664. Min Act: -0.0001

Data Index: 1075435 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 1.9586. Min Range: -1.9586

Max Act: 1.7230. Min Act: -0.0001

Data Index: 543820 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 1.9586. Min Range: -1.9586

Max Act: 1.6537. Min Act: -0.0001

Data Index: 1040970 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 1.9586. Min Range: -1.9586

Max Act: 1.6463. Min Act: -0.0001

Data Index: 1403442 (Python Code)

Max Activating Token Index: 287

Text #11

Max Range: 1.9586. Min Range: -1.9586

Max Act: 1.7205. Min Act: -0.0000

Data Index: 68854 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 1.9586. Min Range: -1.9586

Max Act: 1.4630. Min Act: -0.0000

Data Index: 465062 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 1.9586. Min Range: -1.9586

Max Act: 1.8890. Min Act: -0.0000

Data Index: 1246341 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 1.9586. Min Range: -1.9586

Max Act: 1.4625. Min Act: -0.0000

Data Index: 311371 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 1.9586. Min Range: -1.9586

Max Act: 1.5036. Min Act: -0.0001

Data Index: 1250888 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 1.9586. Min Range: -1.9586

Max Act: 1.4247. Min Act: -0.0000

Data Index: 237047 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 1.9586. Min Range: -1.9586

Max Act: 1.5543. Min Act: -0.0001

Data Index: 1624623 (Python Code)

Max Activating Token Index: 237

Text #18

Max Range: 1.9586. Min Range: -1.9586

Max Act: 1.4814. Min Act: -0.0000

Data Index: 856381 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 1.9586. Min Range: -1.9586

Max Act: 1.6369. Min Act: -0.0000

Data Index: 628124 (C4 (Web Text))

Max Activating Token Index: 933