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

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

Neuron 469 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3690. Min Range: -5.3690

Max Act: 5.2488. Min Act: -0.0000

Data Index: 200836 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 5.3690. Min Range: -5.3690

Max Act: 5.3690. Min Act: -0.0000

Data Index: 842406 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 5.3690. Min Range: -5.3690

Max Act: 5.0612. Min Act: -0.0000

Data Index: 938420 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 5.3690. Min Range: -5.3690

Max Act: 4.8292. Min Act: -0.0000

Data Index: 891536 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 5.3690. Min Range: -5.3690

Max Act: 4.7085. Min Act: -0.0000

Data Index: 1052485 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 5.3690. Min Range: -5.3690

Max Act: 4.7613. Min Act: -0.0000

Data Index: 10755 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 5.3690. Min Range: -5.3690

Max Act: 4.7054. Min Act: -0.0000

Data Index: 1339611 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 5.3690. Min Range: -5.3690

Max Act: 4.4637. Min Act: -0.0000

Data Index: 645738 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 5.3690. Min Range: -5.3690

Max Act: 4.6553. Min Act: -0.0000

Data Index: 854871 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 5.3690. Min Range: -5.3690

Max Act: 4.5935. Min Act: -0.0000

Data Index: 81565 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 5.3690. Min Range: -5.3690

Max Act: 4.4152. Min Act: -0.0000

Data Index: 469743 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 5.3690. Min Range: -5.3690

Max Act: 4.2233. Min Act: -0.0000

Data Index: 327651 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 5.3690. Min Range: -5.3690

Max Act: 4.3978. Min Act: -0.0000

Data Index: 1267986 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 5.3690. Min Range: -5.3690

Max Act: 4.3246. Min Act: -0.0000

Data Index: 578630 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 5.3690. Min Range: -5.3690

Max Act: 3.3247. Min Act: -0.0000

Data Index: 713627 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 5.3690. Min Range: -5.3690

Max Act: 3.4340. Min Act: -0.0000

Data Index: 281853 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 5.3690. Min Range: -5.3690

Max Act: 3.3021. Min Act: -0.0000

Data Index: 1273609 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 5.3690. Min Range: -5.3690

Max Act: 3.3401. Min Act: -0.0000

Data Index: 693491 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 5.3690. Min Range: -5.3690

Max Act: 2.8428. Min Act: -0.0000

Data Index: 268117 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 5.3690. Min Range: -5.3690

Max Act: 3.0957. Min Act: -0.0000

Data Index: 857820 (C4 (Web Text))

Max Activating Token Index: 990