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

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

Neuron 3775 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7287. Min Range: -2.7287

Max Act: 2.7287. Min Act: -0.0000

Data Index: 595376 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 2.7287. Min Range: -2.7287

Max Act: 2.6408. Min Act: -0.0000

Data Index: 334632 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 2.7287. Min Range: -2.7287

Max Act: 2.4232. Min Act: -0.0000

Data Index: 1111238 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 2.7287. Min Range: -2.7287

Max Act: 2.5393. Min Act: -0.0000

Data Index: 639100 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 2.7287. Min Range: -2.7287

Max Act: 2.2843. Min Act: -0.0000

Data Index: 721727 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 2.7287. Min Range: -2.7287

Max Act: 2.2970. Min Act: -0.0000

Data Index: 1164210 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 2.7287. Min Range: -2.7287

Max Act: 2.2645. Min Act: -0.0000

Data Index: 342952 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 2.7287. Min Range: -2.7287

Max Act: 2.2443. Min Act: -0.0000

Data Index: 413382 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 2.7287. Min Range: -2.7287

Max Act: 2.1876. Min Act: -0.0000

Data Index: 326531 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 2.7287. Min Range: -2.7287

Max Act: 2.2938. Min Act: -0.0000

Data Index: 1020521 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 2.7287. Min Range: -2.7287

Max Act: 2.1468. Min Act: -0.0000

Data Index: 1158375 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 2.7287. Min Range: -2.7287

Max Act: 2.1307. Min Act: -0.0000

Data Index: 1289064 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 2.7287. Min Range: -2.7287

Max Act: 2.0797. Min Act: -0.0000

Data Index: 159292 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 2.7287. Min Range: -2.7287

Max Act: 2.1599. Min Act: -0.0000

Data Index: 869642 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 2.7287. Min Range: -2.7287

Max Act: 2.0678. Min Act: -0.0000

Data Index: 1215398 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 2.7287. Min Range: -2.7287

Max Act: 1.9119. Min Act: -0.0000

Data Index: 979502 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 2.7287. Min Range: -2.7287

Max Act: 1.9897. Min Act: -0.0000

Data Index: 835567 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 2.7287. Min Range: -2.7287

Max Act: 2.0837. Min Act: -0.0000

Data Index: 307523 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 2.7287. Min Range: -2.7287

Max Act: 1.9747. Min Act: -0.0000

Data Index: 1224972 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 2.7287. Min Range: -2.7287

Max Act: 1.9587. Min Act: -0.0000

Data Index: 1199303 (C4 (Web Text))

Max Activating Token Index: 771