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

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

Neuron 162 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.4181. Min Act: -0.0001

Data Index: 632818 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3850. Min Act: -0.0000

Data Index: 993003 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3544. Min Act: -0.0000

Data Index: 846939 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3404. Min Act: -0.0001

Data Index: 608631 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3393. Min Act: -0.0000

Data Index: 361157 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3429. Min Act: -0.0001

Data Index: 554336 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3298. Min Act: -0.0001

Data Index: 156056 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3242. Min Act: -0.0001

Data Index: 313177 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3225. Min Act: -0.0000

Data Index: 409172 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3004. Min Act: -0.0001

Data Index: 870415 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3309. Min Act: -0.0000

Data Index: 428658 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.2882. Min Act: -0.0001

Data Index: 1132219 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3046. Min Act: -0.0001

Data Index: 1054027 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3210. Min Act: -0.0000

Data Index: 825177 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3022. Min Act: -0.0001

Data Index: 107922 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.2898. Min Act: -0.0001

Data Index: 740762 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.2900. Min Act: -0.0001

Data Index: 228891 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.2807. Min Act: -0.0001

Data Index: 126272 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.2978. Min Act: -0.0001

Data Index: 1348805 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.2908. Min Act: -0.0001

Data Index: 382576 (C4 (Web Text))

Max Activating Token Index: 888