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

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

Neuron 831 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: 5.5504. Min Range: -5.5504

Max Act: 5.5504. Min Act: -0.0000

Data Index: 970757 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 5.5504. Min Range: -5.5504

Max Act: 5.5088. Min Act: -0.0000

Data Index: 847654 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 5.5504. Min Range: -5.5504

Max Act: 5.1952. Min Act: -0.0000

Data Index: 1105683 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 5.5504. Min Range: -5.5504

Max Act: 5.1319. Min Act: -0.0000

Data Index: 558328 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 5.5504. Min Range: -5.5504

Max Act: 4.5538. Min Act: -0.0000

Data Index: 1096558 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 5.5504. Min Range: -5.5504

Max Act: 5.0001. Min Act: -0.0000

Data Index: 542398 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 5.5504. Min Range: -5.5504

Max Act: 4.9438. Min Act: -0.0000

Data Index: 130756 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 5.5504. Min Range: -5.5504

Max Act: 4.3708. Min Act: -0.0000

Data Index: 800361 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 5.5504. Min Range: -5.5504

Max Act: 4.2290. Min Act: -0.0000

Data Index: 389064 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 5.5504. Min Range: -5.5504

Max Act: 4.1761. Min Act: -0.0000

Data Index: 547836 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 5.5504. Min Range: -5.5504

Max Act: 4.2401. Min Act: -0.0000

Data Index: 1142461 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 5.5504. Min Range: -5.5504

Max Act: 4.0309. Min Act: -0.0000

Data Index: 559781 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 5.5504. Min Range: -5.5504

Max Act: 4.5117. Min Act: -0.0000

Data Index: 1040298 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 5.5504. Min Range: -5.5504

Max Act: 4.1754. Min Act: -0.0000

Data Index: 485698 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 5.5504. Min Range: -5.5504

Max Act: 3.9498. Min Act: -0.0000

Data Index: 457021 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 5.5504. Min Range: -5.5504

Max Act: 3.9259. Min Act: -0.0000

Data Index: 724905 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 5.5504. Min Range: -5.5504

Max Act: 4.3777. Min Act: -0.0000

Data Index: 427597 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 5.5504. Min Range: -5.5504

Max Act: 3.8289. Min Act: -0.0000

Data Index: 901206 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 5.5504. Min Range: -5.5504

Max Act: 4.0041. Min Act: -0.0000

Data Index: 1013548 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 5.5504. Min Range: -5.5504

Max Act: 3.9990. Min Act: -0.0000

Data Index: 942785 (C4 (Web Text))

Max Activating Token Index: 326