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

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

Neuron 3585 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5864. Min Range: -4.5864

Max Act: 4.4885. Min Act: -0.0000

Data Index: 1145876 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 4.5864. Min Range: -4.5864

Max Act: 4.5864. Min Act: -0.0000

Data Index: 1114490 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 4.5864. Min Range: -4.5864

Max Act: 3.7223. Min Act: -0.0000

Data Index: 546889 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 4.5864. Min Range: -4.5864

Max Act: 3.6716. Min Act: -0.0000

Data Index: 629778 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 4.5864. Min Range: -4.5864

Max Act: 3.5171. Min Act: -0.0000

Data Index: 1189042 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 4.5864. Min Range: -4.5864

Max Act: 3.1772. Min Act: -0.0000

Data Index: 1007368 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 4.5864. Min Range: -4.5864

Max Act: 3.4411. Min Act: -0.0000

Data Index: 910464 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 4.5864. Min Range: -4.5864

Max Act: 3.3014. Min Act: -0.0000

Data Index: 574115 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 4.5864. Min Range: -4.5864

Max Act: 3.1351. Min Act: -0.0000

Data Index: 837048 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 4.5864. Min Range: -4.5864

Max Act: 3.1112. Min Act: -0.0000

Data Index: 186638 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 4.5864. Min Range: -4.5864

Max Act: 3.2368. Min Act: -0.0000

Data Index: 151220 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 4.5864. Min Range: -4.5864

Max Act: 3.0402. Min Act: -0.0000

Data Index: 809545 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 4.5864. Min Range: -4.5864

Max Act: 3.0687. Min Act: -0.0000

Data Index: 771659 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 4.5864. Min Range: -4.5864

Max Act: 2.7642. Min Act: -0.0000

Data Index: 994372 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 4.5864. Min Range: -4.5864

Max Act: 2.7191. Min Act: -0.0000

Data Index: 804405 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 4.5864. Min Range: -4.5864

Max Act: 2.8371. Min Act: -0.0000

Data Index: 111873 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 4.5864. Min Range: -4.5864

Max Act: 2.8410. Min Act: -0.0000

Data Index: 1168761 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 4.5864. Min Range: -4.5864

Max Act: 2.8017. Min Act: -0.0000

Data Index: 815891 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 4.5864. Min Range: -4.5864

Max Act: 2.7958. Min Act: -0.0000

Data Index: 759204 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 4.5864. Min Range: -4.5864

Max Act: 2.7431. Min Act: -0.0000

Data Index: 368669 (C4 (Web Text))

Max Activating Token Index: 581