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

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

Neuron 1460 in Layer 1

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: 3.0230. Min Range: -3.0230

Max Act: 3.0230. Min Act: -0.0002

Data Index: 617649 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 3.0230. Min Range: -3.0230

Max Act: 2.7506. Min Act: -0.0002

Data Index: 1114466 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 3.0230. Min Range: -3.0230

Max Act: 2.7355. Min Act: -0.0002

Data Index: 649220 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 3.0230. Min Range: -3.0230

Max Act: 2.6252. Min Act: -0.0002

Data Index: 331300 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 3.0230. Min Range: -3.0230

Max Act: 2.6035. Min Act: -0.0002

Data Index: 195197 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 3.0230. Min Range: -3.0230

Max Act: 2.4869. Min Act: -0.0002

Data Index: 693579 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 3.0230. Min Range: -3.0230

Max Act: 2.4278. Min Act: -0.0002

Data Index: 1205148 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 3.0230. Min Range: -3.0230

Max Act: 2.4140. Min Act: -0.0002

Data Index: 586044 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 3.0230. Min Range: -3.0230

Max Act: 2.4589. Min Act: -0.0002

Data Index: 1329521 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 3.0230. Min Range: -3.0230

Max Act: 2.3732. Min Act: -0.0002

Data Index: 1355852 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 3.0230. Min Range: -3.0230

Max Act: 2.4466. Min Act: -0.0002

Data Index: 476949 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 3.0230. Min Range: -3.0230

Max Act: 2.3314. Min Act: -0.0002

Data Index: 1124283 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 3.0230. Min Range: -3.0230

Max Act: 2.3587. Min Act: -0.0002

Data Index: 321548 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 3.0230. Min Range: -3.0230

Max Act: 2.3493. Min Act: -0.0002

Data Index: 1081737 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 3.0230. Min Range: -3.0230

Max Act: 2.3898. Min Act: -0.0002

Data Index: 781495 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 3.0230. Min Range: -3.0230

Max Act: 2.3435. Min Act: -0.0002

Data Index: 1252196 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 3.0230. Min Range: -3.0230

Max Act: 2.3431. Min Act: -0.0002

Data Index: 1124842 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 3.0230. Min Range: -3.0230

Max Act: 2.3509. Min Act: -0.0002

Data Index: 417508 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 3.0230. Min Range: -3.0230

Max Act: 2.2929. Min Act: -0.0002

Data Index: 539580 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 3.0230. Min Range: -3.0230

Max Act: 2.2662. Min Act: -0.0002

Data Index: 97727 (C4 (Web Text))

Max Activating Token Index: 624