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

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

Neuron 5535 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1232. Min Act: -0.0001

Data Index: 450811 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1310393 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1110. Min Act: -0.0001

Data Index: 267643 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0964. Min Act: -0.0001

Data Index: 777923 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0912. Min Act: -0.0001

Data Index: 1202919 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0904. Min Act: -0.0001

Data Index: 787240 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0935. Min Act: -0.0001

Data Index: 290680 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0955. Min Act: -0.0001

Data Index: 897754 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0895. Min Act: -0.0001

Data Index: 431224 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0825. Min Act: -0.0001

Data Index: 721477 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0818. Min Act: -0.0001

Data Index: 66000 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0848. Min Act: -0.0001

Data Index: 824147 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0899. Min Act: -0.0001

Data Index: 195972 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0842. Min Act: -0.0001

Data Index: 371986 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0820. Min Act: -0.0001

Data Index: 1218231 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0835. Min Act: -0.0001

Data Index: 26743 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0890. Min Act: -0.0001

Data Index: 1193847 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0884. Min Act: -0.0001

Data Index: 543340 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0851. Min Act: -0.0001

Data Index: 234145 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0782. Min Act: -0.0001

Data Index: 913602 (C4 (Web Text))

Max Activating Token Index: 330