Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3497 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.9466. Min Act: -0.0000

Data Index: 205049 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.5120. Min Act: -0.0001

Data Index: 1157261 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.5296. Min Act: -0.0000

Data Index: 504673 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.3110. Min Act: -0.0000

Data Index: 1196360 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.3956. Min Act: -0.0000

Data Index: 1135272 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.3187. Min Act: -0.0000

Data Index: 716343 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.4747. Min Act: -0.0000

Data Index: 475220 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.3133. Min Act: -0.0000

Data Index: 1098868 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.4084. Min Act: -0.0000

Data Index: 394723 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.3715. Min Act: -0.0000

Data Index: 44815 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.3673. Min Act: -0.0000

Data Index: 1183523 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.3406. Min Act: -0.0001

Data Index: 4360 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.3462. Min Act: -0.0001

Data Index: 371920 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.3088. Min Act: -0.0001

Data Index: 455070 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.2582. Min Act: -0.0001

Data Index: 1316741 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.2491. Min Act: -0.0000

Data Index: 172971 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.2255. Min Act: -0.0000

Data Index: 490638 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.3093. Min Act: -0.0000

Data Index: 43376 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.2120. Min Act: -0.0001

Data Index: 1184167 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.2188. Min Act: -0.0000

Data Index: 1212038 (C4 (Web Text))

Max Activating Token Index: 465