Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4759 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.7489. Min Range: -3.7489

Max Act: 3.7489. Min Act: -0.0000

Data Index: 372933 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 3.7489. Min Range: -3.7489

Max Act: 3.2495. Min Act: -0.0000

Data Index: 1191355 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 3.7489. Min Range: -3.7489

Max Act: 3.5990. Min Act: -0.0000

Data Index: 289849 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 3.7489. Min Range: -3.7489

Max Act: 3.5438. Min Act: -0.0000

Data Index: 256135 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 3.7489. Min Range: -3.7489

Max Act: 3.3531. Min Act: -0.0000

Data Index: 474428 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 3.7489. Min Range: -3.7489

Max Act: 3.4515. Min Act: -0.0000

Data Index: 425324 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 3.7489. Min Range: -3.7489

Max Act: 3.5288. Min Act: -0.0001

Data Index: 763833 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 3.7489. Min Range: -3.7489

Max Act: 3.2077. Min Act: -0.0001

Data Index: 209366 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 3.7489. Min Range: -3.7489

Max Act: 3.2485. Min Act: -0.0000

Data Index: 265504 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 3.7489. Min Range: -3.7489

Max Act: 3.2427. Min Act: -0.0000

Data Index: 1209456 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 3.7489. Min Range: -3.7489

Max Act: 2.9353. Min Act: -0.0000

Data Index: 712396 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 3.7489. Min Range: -3.7489

Max Act: 3.0674. Min Act: -0.0000

Data Index: 792198 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 3.7489. Min Range: -3.7489

Max Act: 3.5757. Min Act: -0.0000

Data Index: 122744 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 3.7489. Min Range: -3.7489

Max Act: 2.7028. Min Act: -0.0000

Data Index: 48862 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 3.7489. Min Range: -3.7489

Max Act: 2.6863. Min Act: -0.0000

Data Index: 241670 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 3.7489. Min Range: -3.7489

Max Act: 2.9198. Min Act: -0.0000

Data Index: 525474 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 3.7489. Min Range: -3.7489

Max Act: 2.9266. Min Act: -0.0000

Data Index: 296542 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 3.7489. Min Range: -3.7489

Max Act: 2.9027. Min Act: -0.0000

Data Index: 758504 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 3.7489. Min Range: -3.7489

Max Act: 2.7729. Min Act: -0.0000

Data Index: 264413 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 3.7489. Min Range: -3.7489

Max Act: 2.7469. Min Act: -0.0000

Data Index: 846342 (C4 (Web Text))

Max Activating Token Index: 854