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

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

Neuron 47 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3997. Min Range: -3.3997

Max Act: 3.3997. Min Act: -0.0001

Data Index: 1341556 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 3.3997. Min Range: -3.3997

Max Act: 3.1743. Min Act: -0.0001

Data Index: 534029 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 3.3997. Min Range: -3.3997

Max Act: 3.2495. Min Act: -0.0001

Data Index: 694077 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 3.3997. Min Range: -3.3997

Max Act: 3.0271. Min Act: -0.0001

Data Index: 761489 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 3.3997. Min Range: -3.3997

Max Act: 2.9851. Min Act: -0.0001

Data Index: 466883 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 3.3997. Min Range: -3.3997

Max Act: 2.9633. Min Act: -0.0000

Data Index: 532482 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 3.3997. Min Range: -3.3997

Max Act: 3.0757. Min Act: -0.0001

Data Index: 1211993 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 3.3997. Min Range: -3.3997

Max Act: 3.3904. Min Act: -0.0001

Data Index: 166039 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 3.3997. Min Range: -3.3997

Max Act: 3.0535. Min Act: -0.0000

Data Index: 236192 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 3.3997. Min Range: -3.3997

Max Act: 2.7817. Min Act: -0.0001

Data Index: 325658 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 3.3997. Min Range: -3.3997

Max Act: 2.8712. Min Act: -0.0001

Data Index: 562833 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 3.3997. Min Range: -3.3997

Max Act: 2.8168. Min Act: -0.0001

Data Index: 1172399 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 3.3997. Min Range: -3.3997

Max Act: 2.7289. Min Act: -0.0001

Data Index: 607833 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 3.3997. Min Range: -3.3997

Max Act: 2.8328. Min Act: -0.0001

Data Index: 1122376 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 3.3997. Min Range: -3.3997

Max Act: 2.7997. Min Act: -0.0001

Data Index: 317987 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 3.3997. Min Range: -3.3997

Max Act: 2.5909. Min Act: -0.0001

Data Index: 1094347 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 3.3997. Min Range: -3.3997

Max Act: 2.6144. Min Act: -0.0001

Data Index: 264909 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 3.3997. Min Range: -3.3997

Max Act: 2.7145. Min Act: -0.0001

Data Index: 478283 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 3.3997. Min Range: -3.3997

Max Act: 2.6783. Min Act: -0.0001

Data Index: 214842 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 3.3997. Min Range: -3.3997

Max Act: 2.6285. Min Act: -0.0001

Data Index: 573706 (C4 (Web Text))

Max Activating Token Index: 125