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

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

Neuron 2064 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 6.7741. Min Range: -6.7741

Max Act: 6.7741. Min Act: -0.0001

Data Index: 1276927 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 6.7741. Min Range: -6.7741

Max Act: 6.7470. Min Act: -0.0001

Data Index: 131598 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 6.7741. Min Range: -6.7741

Max Act: 5.3672. Min Act: -0.0001

Data Index: 376250 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 6.7741. Min Range: -6.7741

Max Act: 5.3848. Min Act: -0.0001

Data Index: 1124992 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 6.7741. Min Range: -6.7741

Max Act: 5.2800. Min Act: -0.0001

Data Index: 166442 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 6.7741. Min Range: -6.7741

Max Act: 5.2739. Min Act: -0.0001

Data Index: 1101717 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 6.7741. Min Range: -6.7741

Max Act: 4.9161. Min Act: -0.0001

Data Index: 184671 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 6.7741. Min Range: -6.7741

Max Act: 4.7863. Min Act: -0.0001

Data Index: 59428 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 6.7741. Min Range: -6.7741

Max Act: 4.9056. Min Act: -0.0001

Data Index: 710206 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 6.7741. Min Range: -6.7741

Max Act: 4.8404. Min Act: -0.0001

Data Index: 702609 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 6.7741. Min Range: -6.7741

Max Act: 4.8497. Min Act: -0.0001

Data Index: 805719 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 6.7741. Min Range: -6.7741

Max Act: 4.7992. Min Act: -0.0001

Data Index: 715074 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 6.7741. Min Range: -6.7741

Max Act: 4.6455. Min Act: -0.0001

Data Index: 947228 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 6.7741. Min Range: -6.7741

Max Act: 4.5166. Min Act: -0.0001

Data Index: 639777 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 6.7741. Min Range: -6.7741

Max Act: 4.6779. Min Act: -0.0001

Data Index: 292855 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 6.7741. Min Range: -6.7741

Max Act: 4.6549. Min Act: -0.0001

Data Index: 201798 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 6.7741. Min Range: -6.7741

Max Act: 4.5277. Min Act: -0.0001

Data Index: 455067 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 6.7741. Min Range: -6.7741

Max Act: 4.6106. Min Act: -0.0001

Data Index: 38235 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 6.7741. Min Range: -6.7741

Max Act: 4.5301. Min Act: -0.0001

Data Index: 685477 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 6.7741. Min Range: -6.7741

Max Act: 4.5052. Min Act: -0.0001

Data Index: 1288703 (C4 (Web Text))

Max Activating Token Index: 865