Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 822 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.6990. Min Act: -0.0001

Data Index: 131 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.3177. Min Act: -0.0001

Data Index: 608857 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.3016. Min Act: -0.0001

Data Index: 700293 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.2220. Min Act: -0.0001

Data Index: 1103990 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.9137. Min Act: -0.0001

Data Index: 530686 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.9820. Min Act: -0.0001

Data Index: 1260691 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.9073. Min Act: -0.0001

Data Index: 503318 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.8495. Min Act: -0.0001

Data Index: 1080507 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.8351. Min Act: -0.0001

Data Index: 108416 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.6385. Min Act: -0.0001

Data Index: 817224 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.7457. Min Act: -0.0001

Data Index: 979268 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.7839. Min Act: -0.0001

Data Index: 32132 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.7754. Min Act: -0.0001

Data Index: 1004467 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.7781. Min Act: -0.0001

Data Index: 537763 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.6545. Min Act: -0.0001

Data Index: 1108600 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.7284. Min Act: -0.0001

Data Index: 678988 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.7489. Min Act: -0.0001

Data Index: 931107 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.7317. Min Act: -0.0001

Data Index: 1563929 (Python Code)

Max Activating Token Index: 852

Text #18

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.7089. Min Act: -0.0001

Data Index: 1049579 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 1.6990. Min Range: -1.6990

Max Act: 0.7058. Min Act: -0.0001

Data Index: 1379208 (Python Code)

Max Activating Token Index: 734