Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 502 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0307. Min Act: -0.0006

Data Index: 159832 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1026761 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0257. Min Act: -0.0006

Data Index: 103545 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0253. Min Act: -0.0006

Data Index: 1076631 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0259. Min Act: -0.0006

Data Index: 1117628 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0262. Min Act: -0.0006

Data Index: 425771 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0256. Min Act: -0.0006

Data Index: 826900 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1238775 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0246. Min Act: -0.0006

Data Index: 845600 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0244. Min Act: -0.0006

Data Index: 558364 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0242. Min Act: -0.0006

Data Index: 179265 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0245. Min Act: -0.0006

Data Index: 349070 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0240. Min Act: -0.0006

Data Index: 366741 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0243. Min Act: -0.0006

Data Index: 474268 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0233. Min Act: -0.0006

Data Index: 1096614 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0242. Min Act: -0.0006

Data Index: 288840 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0241. Min Act: -0.0006

Data Index: 427711 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0245. Min Act: -0.0006

Data Index: 701651 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0246. Min Act: -0.0006

Data Index: 997234 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0233. Min Act: -0.0006

Data Index: 457008 (C4 (Web Text))

Max Activating Token Index: 179