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

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

Neuron 5712 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: 1.5208. Min Range: -1.5208

Max Act: 1.5208. Min Act: -0.0001

Data Index: 124172 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.4129. Min Act: -0.0002

Data Index: 337516 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.3680. Min Act: -0.0001

Data Index: 740143 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.3765. Min Act: -0.0001

Data Index: 1079799 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.3164. Min Act: -0.0001

Data Index: 351813 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.2980. Min Act: -0.0001

Data Index: 1265722 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.3248. Min Act: -0.0001

Data Index: 971937 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.2900. Min Act: -0.0001

Data Index: 112224 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.2822. Min Act: -0.0002

Data Index: 500508 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.2825. Min Act: -0.0001

Data Index: 624356 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.3065. Min Act: -0.0001

Data Index: 1133475 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.2837. Min Act: -0.0001

Data Index: 366014 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.2809. Min Act: -0.0001

Data Index: 909565 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.2671. Min Act: -0.0001

Data Index: 853613 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.2877. Min Act: -0.0001

Data Index: 1273598 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.2510. Min Act: -0.0001

Data Index: 122810 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.2766. Min Act: -0.0001

Data Index: 1356471 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.2814. Min Act: -0.0001

Data Index: 710310 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.2342. Min Act: -0.0001

Data Index: 1075221 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.2669. Min Act: -0.0001

Data Index: 801604 (C4 (Web Text))

Max Activating Token Index: 473