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

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

Neuron 4053 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9193. Min Range: -2.9193

Max Act: 2.9193. Min Act: -0.0000

Data Index: 1224793 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 2.9193. Min Range: -2.9193

Max Act: 2.7406. Min Act: -0.0000

Data Index: 1128257 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 2.9193. Min Range: -2.9193

Max Act: 2.5346. Min Act: -0.0000

Data Index: 74969 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 2.9193. Min Range: -2.9193

Max Act: 2.3691. Min Act: -0.0000

Data Index: 282975 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 2.9193. Min Range: -2.9193

Max Act: 2.3542. Min Act: -0.0000

Data Index: 1256195 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 2.9193. Min Range: -2.9193

Max Act: 2.4712. Min Act: -0.0000

Data Index: 231194 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 2.9193. Min Range: -2.9193

Max Act: 2.2443. Min Act: -0.0000

Data Index: 452188 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 2.9193. Min Range: -2.9193

Max Act: 2.3957. Min Act: -0.0000

Data Index: 1401222 (Python Code)

Max Activating Token Index: 552

Text #8

Max Range: 2.9193. Min Range: -2.9193

Max Act: 2.0820. Min Act: -0.0000

Data Index: 439124 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 2.9193. Min Range: -2.9193

Max Act: 2.0507. Min Act: -0.0000

Data Index: 124145 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 2.9193. Min Range: -2.9193

Max Act: 2.2623. Min Act: -0.0000

Data Index: 941216 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 2.9193. Min Range: -2.9193

Max Act: 2.1392. Min Act: -0.0000

Data Index: 1497788 (Python Code)

Max Activating Token Index: 195

Text #12

Max Range: 2.9193. Min Range: -2.9193

Max Act: 2.2487. Min Act: -0.0000

Data Index: 1222201 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 2.9193. Min Range: -2.9193

Max Act: 2.3482. Min Act: -0.0000

Data Index: 1643252 (Python Code)

Max Activating Token Index: 461

Text #14

Max Range: 2.9193. Min Range: -2.9193

Max Act: 2.1276. Min Act: -0.0000

Data Index: 1316069 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 2.9193. Min Range: -2.9193

Max Act: 2.2439. Min Act: -0.0000

Data Index: 707977 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 2.9193. Min Range: -2.9193

Max Act: 2.2134. Min Act: -0.0000

Data Index: 431506 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 2.9193. Min Range: -2.9193

Max Act: 2.2182. Min Act: -0.0000

Data Index: 556633 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 2.9193. Min Range: -2.9193

Max Act: 2.1665. Min Act: -0.0000

Data Index: 676116 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 2.9193. Min Range: -2.9193

Max Act: 2.0501. Min Act: -0.0000

Data Index: 1054143 (C4 (Web Text))

Max Activating Token Index: 140