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

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

Neuron 4363 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.5739. Min Act: -0.0000

Data Index: 1098604 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.4235. Min Act: -0.0000

Data Index: 601478 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.7114. Min Act: -0.0000

Data Index: 851771 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.4055. Min Act: -0.0000

Data Index: 856701 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.5635. Min Act: -0.0000

Data Index: 1053259 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.4217. Min Act: -0.0000

Data Index: 729151 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.4920. Min Act: -0.0000

Data Index: 1053291 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.3385. Min Act: -0.0000

Data Index: 900528 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.4498. Min Act: -0.0000

Data Index: 31320 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.4098. Min Act: -0.0000

Data Index: 932188 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.2271. Min Act: -0.0000

Data Index: 40946 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.3716. Min Act: -0.0000

Data Index: 788559 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.3213. Min Act: -0.0001

Data Index: 661402 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.3131. Min Act: -0.0001

Data Index: 995067 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.2176. Min Act: -0.0000

Data Index: 639235 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.2189. Min Act: -0.0000

Data Index: 780788 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.3581. Min Act: -0.0001

Data Index: 253611 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.2545. Min Act: -0.0000

Data Index: 1288867 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.1050. Min Act: -0.0001

Data Index: 914770 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 3.7114. Min Range: -3.7114

Max Act: 3.1173. Min Act: -0.0000

Data Index: 451614 (C4 (Web Text))

Max Activating Token Index: 53