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

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

Neuron 564 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.4633. Min Act: -0.0001

Data Index: 905500 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.4177. Min Act: -0.0001

Data Index: 995526 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3935. Min Act: -0.0001

Data Index: 1339380 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3772. Min Act: -0.0001

Data Index: 650299 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3646. Min Act: -0.0001

Data Index: 895684 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3888. Min Act: -0.0001

Data Index: 1347444 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3632. Min Act: -0.0001

Data Index: 593883 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.4268. Min Act: -0.0001

Data Index: 220252 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3695. Min Act: -0.0001

Data Index: 203195 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3552. Min Act: -0.0001

Data Index: 490869 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3571. Min Act: -0.0001

Data Index: 728651 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3415. Min Act: -0.0001

Data Index: 787149 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3416. Min Act: -0.0001

Data Index: 489626 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3186. Min Act: -0.0001

Data Index: 641454 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3168. Min Act: -0.0001

Data Index: 1145438 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3205. Min Act: -0.0001

Data Index: 72257 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.2952. Min Act: -0.0001

Data Index: 282310 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.2957. Min Act: -0.0001

Data Index: 275497 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.2655. Min Act: -0.0001

Data Index: 82277 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.2890. Min Act: -0.0001

Data Index: 147848 (C4 (Web Text))

Max Activating Token Index: 446