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

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

Neuron 1093 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: 4.2311. Min Range: -4.2311

Max Act: 4.2311. Min Act: -0.0000

Data Index: 682140 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 4.2311. Min Range: -4.2311

Max Act: 3.9690. Min Act: -0.0000

Data Index: 116142 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 4.2311. Min Range: -4.2311

Max Act: 3.9089. Min Act: -0.0000

Data Index: 305528 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 4.2311. Min Range: -4.2311

Max Act: 3.8767. Min Act: -0.0000

Data Index: 302403 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 4.2311. Min Range: -4.2311

Max Act: 3.5217. Min Act: -0.0000

Data Index: 802559 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 4.2311. Min Range: -4.2311

Max Act: 3.4978. Min Act: -0.0000

Data Index: 1232068 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 4.2311. Min Range: -4.2311

Max Act: 3.3953. Min Act: -0.0000

Data Index: 957587 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 4.2311. Min Range: -4.2311

Max Act: 3.3182. Min Act: -0.0000

Data Index: 644100 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 4.2311. Min Range: -4.2311

Max Act: 3.4485. Min Act: -0.0000

Data Index: 263703 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 4.2311. Min Range: -4.2311

Max Act: 3.1183. Min Act: -0.0000

Data Index: 1086502 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 4.2311. Min Range: -4.2311

Max Act: 2.9674. Min Act: -0.0000

Data Index: 697842 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 4.2311. Min Range: -4.2311

Max Act: 2.9111. Min Act: -0.0000

Data Index: 1212904 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 4.2311. Min Range: -4.2311

Max Act: 3.0131. Min Act: -0.0000

Data Index: 1087369 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 4.2311. Min Range: -4.2311

Max Act: 3.1636. Min Act: -0.0000

Data Index: 784480 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 4.2311. Min Range: -4.2311

Max Act: 2.8227. Min Act: -0.0000

Data Index: 196886 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 4.2311. Min Range: -4.2311

Max Act: 2.9459. Min Act: -0.0000

Data Index: 1081327 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 4.2311. Min Range: -4.2311

Max Act: 2.7179. Min Act: -0.0000

Data Index: 727834 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 4.2311. Min Range: -4.2311

Max Act: 2.8221. Min Act: -0.0000

Data Index: 1025736 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 4.2311. Min Range: -4.2311

Max Act: 2.6875. Min Act: -0.0000

Data Index: 547595 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 4.2311. Min Range: -4.2311

Max Act: 2.6758. Min Act: -0.0000

Data Index: 14649 (C4 (Web Text))

Max Activating Token Index: 488