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

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

Neuron 2775 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.4789. Min Act: -0.0001

Data Index: 755214 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3788. Min Act: -0.0001

Data Index: 1136066 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.4063. Min Act: -0.0001

Data Index: 267749 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3468. Min Act: -0.0001

Data Index: 482488 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3120. Min Act: -0.0001

Data Index: 1160197 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3203. Min Act: -0.0001

Data Index: 352316 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3103. Min Act: -0.0001

Data Index: 418682 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3089. Min Act: -0.0001

Data Index: 414786 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3283. Min Act: -0.0001

Data Index: 284514 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3251. Min Act: -0.0001

Data Index: 237245 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3002. Min Act: -0.0001

Data Index: 1122528 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.2990. Min Act: -0.0000

Data Index: 920768 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.2972. Min Act: -0.0001

Data Index: 797492 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3213. Min Act: -0.0001

Data Index: 314116 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3027. Min Act: -0.0001

Data Index: 191355 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.2800. Min Act: -0.0001

Data Index: 1152517 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.2918. Min Act: -0.0000

Data Index: 994898 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.2707. Min Act: -0.0001

Data Index: 1010813 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.2877. Min Act: -0.0001

Data Index: 62948 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.2876. Min Act: -0.0001

Data Index: 323139 (C4 (Web Text))

Max Activating Token Index: 400