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

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

Neuron 2267 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: 2.3012. Min Range: -2.3012

Max Act: 2.3012. Min Act: -0.0000

Data Index: 490404 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 2.3012. Min Range: -2.3012

Max Act: 2.1351. Min Act: -0.0000

Data Index: 418969 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 2.3012. Min Range: -2.3012

Max Act: 1.6872. Min Act: -0.0000

Data Index: 423453 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 2.3012. Min Range: -2.3012

Max Act: 1.8293. Min Act: -0.0000

Data Index: 638180 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 2.3012. Min Range: -2.3012

Max Act: 1.7787. Min Act: -0.0000

Data Index: 561396 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 2.3012. Min Range: -2.3012

Max Act: 1.6906. Min Act: -0.0000

Data Index: 361851 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 2.3012. Min Range: -2.3012

Max Act: 1.6409. Min Act: -0.0000

Data Index: 1144887 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 2.3012. Min Range: -2.3012

Max Act: 1.6514. Min Act: -0.0000

Data Index: 415608 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 2.3012. Min Range: -2.3012

Max Act: 1.6267. Min Act: -0.0000

Data Index: 1270718 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 2.3012. Min Range: -2.3012

Max Act: 1.5368. Min Act: -0.0000

Data Index: 1016472 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 2.3012. Min Range: -2.3012

Max Act: 1.5325. Min Act: -0.0000

Data Index: 628830 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 2.3012. Min Range: -2.3012

Max Act: 1.4921. Min Act: -0.0000

Data Index: 501346 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 2.3012. Min Range: -2.3012

Max Act: 1.4860. Min Act: -0.0000

Data Index: 938210 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 2.3012. Min Range: -2.3012

Max Act: 1.5168. Min Act: -0.0000

Data Index: 1185674 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 2.3012. Min Range: -2.3012

Max Act: 1.3999. Min Act: -0.0000

Data Index: 198334 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 2.3012. Min Range: -2.3012

Max Act: 1.5319. Min Act: -0.0000

Data Index: 1128160 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 2.3012. Min Range: -2.3012

Max Act: 1.5207. Min Act: -0.0000

Data Index: 323002 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 2.3012. Min Range: -2.3012

Max Act: 1.3080. Min Act: -0.0000

Data Index: 1344224 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 2.3012. Min Range: -2.3012

Max Act: 1.4350. Min Act: -0.0000

Data Index: 1195970 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 2.3012. Min Range: -2.3012

Max Act: 1.5305. Min Act: -0.0000

Data Index: 249385 (C4 (Web Text))

Max Activating Token Index: 198