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

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

Neuron 982 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: 3.4967. Min Range: -3.4967

Max Act: 3.4967. Min Act: -0.1700

Data Index: 233588 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.4892. Min Act: -0.1700

Data Index: 876992 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.4300. Min Act: -0.1700

Data Index: 882880 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.4167. Min Act: -0.1700

Data Index: 214082 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.4063. Min Act: -0.1700

Data Index: 1294705 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.3968. Min Act: -0.1700

Data Index: 208939 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.3832. Min Act: -0.1700

Data Index: 499494 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.3622. Min Act: -0.1700

Data Index: 297913 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.3596. Min Act: -0.1700

Data Index: 1013192 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.3386. Min Act: -0.1700

Data Index: 713881 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.3322. Min Act: -0.1700

Data Index: 1062803 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.3436. Min Act: -0.1700

Data Index: 227440 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.3118. Min Act: -0.1700

Data Index: 515739 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.3314. Min Act: -0.1700

Data Index: 419581 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.3112. Min Act: -0.1700

Data Index: 858060 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.3137. Min Act: -0.1700

Data Index: 1165207 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.2789. Min Act: -0.1700

Data Index: 1275857 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.2933. Min Act: -0.1700

Data Index: 902631 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.2675. Min Act: -0.1700

Data Index: 275858 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.2808. Min Act: -0.1700

Data Index: 1249703 (C4 (Web Text))

Max Activating Token Index: 427