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

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

Neuron 1049 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.4860. Min Act: -0.0000

Data Index: 556169 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.4759. Min Act: -0.0000

Data Index: 1355555 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3961. Min Act: -0.0000

Data Index: 248502 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3922. Min Act: -0.0000

Data Index: 1098625 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.4059. Min Act: -0.0000

Data Index: 1299279 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.4042. Min Act: -0.0000

Data Index: 263336 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3765. Min Act: -0.0000

Data Index: 668675 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3496. Min Act: -0.0000

Data Index: 1127852 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3450. Min Act: -0.0000

Data Index: 405396 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3397. Min Act: -0.0000

Data Index: 451074 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3192. Min Act: -0.0000

Data Index: 456226 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3094. Min Act: -0.0000

Data Index: 126830 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3092. Min Act: -0.0000

Data Index: 302066 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3049. Min Act: -0.0000

Data Index: 318253 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3240. Min Act: -0.0000

Data Index: 1358851 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3017. Min Act: -0.0000

Data Index: 366923 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3149. Min Act: -0.0000

Data Index: 228691 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3104. Min Act: -0.0000

Data Index: 109317 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3200. Min Act: -0.0000

Data Index: 621521 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.2979. Min Act: -0.0000

Data Index: 282809 (C4 (Web Text))

Max Activating Token Index: 337