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

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

Neuron 3885 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1764. Min Range: -2.1764

Max Act: 2.0611. Min Act: 0.0000

Data Index: 1309396 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 2.1764. Min Range: -2.1764

Max Act: 2.1764. Min Act: -0.0000

Data Index: 106727 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.9997. Min Act: -0.0000

Data Index: 1110350 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.8824. Min Act: -0.0000

Data Index: 1092734 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.6654. Min Act: -0.0000

Data Index: 725241 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.5335. Min Act: -0.0000

Data Index: 1126952 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.8398. Min Act: -0.0000

Data Index: 1199094 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.5985. Min Act: -0.0000

Data Index: 82310 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.5937. Min Act: -0.0000

Data Index: 210629 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.6684. Min Act: -0.0000

Data Index: 713749 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.5330. Min Act: -0.0000

Data Index: 543180 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.5209. Min Act: -0.0000

Data Index: 1141607 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.4704. Min Act: -0.0000

Data Index: 1343025 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.3678. Min Act: -0.0000

Data Index: 583439 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.4234. Min Act: -0.0000

Data Index: 1351590 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.3996. Min Act: -0.0000

Data Index: 1207217 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.3747. Min Act: -0.0000

Data Index: 1432150 (Python Code)

Max Activating Token Index: 277

Text #17

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.3457. Min Act: -0.0000

Data Index: 388238 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.2706. Min Act: -0.0000

Data Index: 1511815 (Python Code)

Max Activating Token Index: 552

Text #19

Max Range: 2.1764. Min Range: -2.1764

Max Act: 1.2239. Min Act: -0.0000

Data Index: 82566 (C4 (Web Text))

Max Activating Token Index: 763