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

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

Neuron 4795 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.4162. Min Act: -0.0000

Data Index: 456655 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.4122. Min Act: -0.0000

Data Index: 838 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.3808. Min Act: -0.0000

Data Index: 643845 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.3129. Min Act: -0.0000

Data Index: 326081 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.2257. Min Act: -0.0000

Data Index: 21602 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.2922. Min Act: -0.0000

Data Index: 803453 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.2903. Min Act: -0.0000

Data Index: 1340163 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.2078. Min Act: -0.0000

Data Index: 181616 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.2728. Min Act: -0.0000

Data Index: 697507 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.2631. Min Act: -0.0000

Data Index: 661404 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.3050. Min Act: -0.0000

Data Index: 4976 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.2346. Min Act: -0.0000

Data Index: 624092 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.2218. Min Act: -0.0000

Data Index: 51371 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.1312. Min Act: -0.0000

Data Index: 961162 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.1369. Min Act: -0.0000

Data Index: 930756 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.2448. Min Act: -0.0000

Data Index: 385643 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.0857. Min Act: -0.0000

Data Index: 683044 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.0157. Min Act: -0.0000

Data Index: 295662 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.1249. Min Act: -0.0000

Data Index: 673966 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 1.4162. Min Range: -1.4162

Max Act: 1.1983. Min Act: -0.0000

Data Index: 346392 (C4 (Web Text))

Max Activating Token Index: 583