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

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

Neuron 3022 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3747. Min Range: -2.3747

Max Act: 2.3747. Min Act: -0.0000

Data Index: 565466 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 2.3747. Min Range: -2.3747

Max Act: 2.3347. Min Act: -0.0000

Data Index: 537075 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 2.3747. Min Range: -2.3747

Max Act: 2.2540. Min Act: -0.0000

Data Index: 1139106 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 2.3747. Min Range: -2.3747

Max Act: 2.1200. Min Act: -0.0000

Data Index: 310704 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 2.3747. Min Range: -2.3747

Max Act: 1.8428. Min Act: -0.0000

Data Index: 919181 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 2.3747. Min Range: -2.3747

Max Act: 1.7401. Min Act: -0.0000

Data Index: 159146 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 2.3747. Min Range: -2.3747

Max Act: 1.6313. Min Act: -0.0000

Data Index: 724753 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 2.3747. Min Range: -2.3747

Max Act: 1.7015. Min Act: -0.0000

Data Index: 23315 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 2.3747. Min Range: -2.3747

Max Act: 1.8405. Min Act: -0.0000

Data Index: 1004224 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 2.3747. Min Range: -2.3747

Max Act: 1.6495. Min Act: -0.0000

Data Index: 944300 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 2.3747. Min Range: -2.3747

Max Act: 1.5158. Min Act: -0.0000

Data Index: 427755 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 2.3747. Min Range: -2.3747

Max Act: 1.5952. Min Act: -0.0000

Data Index: 676671 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 2.3747. Min Range: -2.3747

Max Act: 1.3774. Min Act: -0.0000

Data Index: 1021247 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 2.3747. Min Range: -2.3747

Max Act: 1.5792. Min Act: -0.0000

Data Index: 580071 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 2.3747. Min Range: -2.3747

Max Act: 1.5127. Min Act: -0.0000

Data Index: 1308680 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 2.3747. Min Range: -2.3747

Max Act: 1.5945. Min Act: -0.0000

Data Index: 340338 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 2.3747. Min Range: -2.3747

Max Act: 1.5703. Min Act: -0.0000

Data Index: 341124 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 2.3747. Min Range: -2.3747

Max Act: 1.4454. Min Act: -0.0000

Data Index: 1117 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 2.3747. Min Range: -2.3747

Max Act: 1.3765. Min Act: -0.0000

Data Index: 1033508 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 2.3747. Min Range: -2.3747

Max Act: 1.4823. Min Act: -0.0000

Data Index: 343312 (C4 (Web Text))

Max Activating Token Index: 956