Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 340 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.1888. Min Range: -3.1888

Max Act: 3.1787. Min Act: -0.1700

Data Index: 926844 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 3.1888. Min Range: -3.1888

Max Act: 3.1883. Min Act: -0.1700

Data Index: 55902 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 3.1888. Min Range: -3.1888

Max Act: 3.1874. Min Act: -0.1700

Data Index: 843642 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 3.1888. Min Range: -3.1888

Max Act: 3.1888. Min Act: -0.1700

Data Index: 1212605 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 3.1888. Min Range: -3.1888

Max Act: 3.1655. Min Act: -0.1700

Data Index: 736680 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 3.1888. Min Range: -3.1888

Max Act: 3.1490. Min Act: -0.1700

Data Index: 282988 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 3.1888. Min Range: -3.1888

Max Act: 3.1549. Min Act: -0.1700

Data Index: 661709 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 3.1888. Min Range: -3.1888

Max Act: 3.1543. Min Act: -0.1700

Data Index: 165483 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 3.1888. Min Range: -3.1888

Max Act: 3.1665. Min Act: -0.1700

Data Index: 608850 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 3.1888. Min Range: -3.1888

Max Act: 3.1524. Min Act: -0.1700

Data Index: 154357 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 3.1888. Min Range: -3.1888

Max Act: 3.1141. Min Act: -0.1700

Data Index: 60696 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 3.1888. Min Range: -3.1888

Max Act: 3.1170. Min Act: -0.1700

Data Index: 1013748 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 3.1888. Min Range: -3.1888

Max Act: 3.1125. Min Act: -0.1700

Data Index: 756499 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 3.1888. Min Range: -3.1888

Max Act: 3.1041. Min Act: -0.1700

Data Index: 43064 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 3.1888. Min Range: -3.1888

Max Act: 3.0892. Min Act: -0.1700

Data Index: 686046 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 3.1888. Min Range: -3.1888

Max Act: 3.1050. Min Act: -0.1700

Data Index: 548653 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 3.1888. Min Range: -3.1888

Max Act: 3.0874. Min Act: -0.1700

Data Index: 1000323 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 3.1888. Min Range: -3.1888

Max Act: 3.0697. Min Act: -0.1700

Data Index: 924499 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 3.1888. Min Range: -3.1888

Max Act: 3.0565. Min Act: -0.1700

Data Index: 1097273 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 3.1888. Min Range: -3.1888

Max Act: 3.0352. Min Act: -0.1700

Data Index: 685104 (C4 (Web Text))

Max Activating Token Index: 22