Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 580 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0002

Data Index: 1323608 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0305. Min Act: -0.0002

Data Index: 113689 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0290. Min Act: -0.0002

Data Index: 766998 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0288. Min Act: -0.0002

Data Index: 303982 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0279. Min Act: -0.0002

Data Index: 641347 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1015428 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0261. Min Act: -0.0003

Data Index: 698067 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0257. Min Act: -0.0002

Data Index: 802571 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0250. Min Act: -0.0003

Data Index: 143956 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0249. Min Act: -0.0002

Data Index: 577658 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1153874 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0247. Min Act: -0.0003

Data Index: 565463 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1159453 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0247. Min Act: -0.0002

Data Index: 690236 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0247. Min Act: -0.0002

Data Index: 857565 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0247. Min Act: -0.0003

Data Index: 1536214 (Python Code)

Max Activating Token Index: 306

Text #16

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0240. Min Act: -0.0003

Data Index: 1284938 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0241. Min Act: -0.0002

Data Index: 306008 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0244. Min Act: -0.0002

Data Index: 98049 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0240. Min Act: -0.0003

Data Index: 1245867 (C4 (Web Text))

Max Activating Token Index: 639