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

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

Neuron 751 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: 3.8312. Min Range: -3.8312

Max Act: 3.8093. Min Act: -0.0000

Data Index: 469743 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.7378. Min Act: -0.0000

Data Index: 783334 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.8312. Min Act: -0.0000

Data Index: 1087678 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.6719. Min Act: -0.0000

Data Index: 553281 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.3433. Min Act: -0.0000

Data Index: 111486 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.6482. Min Act: -0.0000

Data Index: 351382 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.3945. Min Act: -0.0000

Data Index: 139320 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.2229. Min Act: -0.0000

Data Index: 107742 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.2904. Min Act: -0.0000

Data Index: 10949 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.1024. Min Act: -0.0000

Data Index: 415527 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 3.8312. Min Range: -3.8312

Max Act: 2.9590. Min Act: -0.0000

Data Index: 223321 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.1521. Min Act: -0.0000

Data Index: 248093 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.1386. Min Act: -0.0000

Data Index: 473733 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 3.8312. Min Range: -3.8312

Max Act: 3.1374. Min Act: -0.0000

Data Index: 1348793 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 3.8312. Min Range: -3.8312

Max Act: 2.8901. Min Act: -0.0000

Data Index: 610995 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 3.8312. Min Range: -3.8312

Max Act: 2.8261. Min Act: -0.0000

Data Index: 43296 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 3.8312. Min Range: -3.8312

Max Act: 2.7986. Min Act: -0.0000

Data Index: 253720 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 3.8312. Min Range: -3.8312

Max Act: 2.7345. Min Act: -0.0000

Data Index: 861238 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 3.8312. Min Range: -3.8312

Max Act: 2.8077. Min Act: -0.0000

Data Index: 206145 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 3.8312. Min Range: -3.8312

Max Act: 2.6703. Min Act: -0.0000

Data Index: 777501 (C4 (Web Text))

Max Activating Token Index: 726