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

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

Neuron 2017 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.7820. Min Act: -0.0000

Data Index: 230177 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.4859. Min Act: -0.0000

Data Index: 80695 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.3858. Min Act: -0.0000

Data Index: 362577 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.3706. Min Act: -0.0000

Data Index: 574046 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.3475. Min Act: -0.0000

Data Index: 672958 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.4157. Min Act: -0.0000

Data Index: 496934 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.1816. Min Act: -0.0000

Data Index: 906306 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.1975. Min Act: -0.0000

Data Index: 414348 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.3474. Min Act: -0.0000

Data Index: 668564 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.3191. Min Act: -0.0000

Data Index: 1221628 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.3276. Min Act: -0.0000

Data Index: 934483 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.1178. Min Act: -0.0000

Data Index: 773453 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.2752. Min Act: -0.0000

Data Index: 147670 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.1003. Min Act: -0.0000

Data Index: 799190 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.2815. Min Act: -0.0000

Data Index: 18256 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.2653. Min Act: -0.0000

Data Index: 271140 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.2133. Min Act: -0.0000

Data Index: 1222254 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.2030. Min Act: -0.0000

Data Index: 1316729 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.1960. Min Act: -0.0000

Data Index: 166163 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.3680. Min Act: -0.0000

Data Index: 261144 (C4 (Web Text))

Max Activating Token Index: 1008