Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 386 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5145. Min Range: -3.5145

Max Act: 3.5145. Min Act: -0.1700

Data Index: 464359 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 3.5145. Min Range: -3.5145

Max Act: 3.4832. Min Act: -0.1700

Data Index: 391635 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 3.5145. Min Range: -3.5145

Max Act: 3.4832. Min Act: -0.1700

Data Index: 1114277 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 3.5145. Min Range: -3.5145

Max Act: 3.4675. Min Act: -0.1700

Data Index: 67013 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 3.5145. Min Range: -3.5145

Max Act: 3.4989. Min Act: -0.1700

Data Index: 692453 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 3.5145. Min Range: -3.5145

Max Act: 3.4362. Min Act: -0.1700

Data Index: 610734 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 3.5145. Min Range: -3.5145

Max Act: 3.4519. Min Act: -0.1700

Data Index: 359189 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 3.5145. Min Range: -3.5145

Max Act: 3.4205. Min Act: -0.1700

Data Index: 191274 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 3.5145. Min Range: -3.5145

Max Act: 3.4048. Min Act: -0.1700

Data Index: 567563 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 3.5145. Min Range: -3.5145

Max Act: 3.4048. Min Act: -0.1700

Data Index: 142229 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 3.5145. Min Range: -3.5145

Max Act: 3.4205. Min Act: -0.1700

Data Index: 1293779 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 3.5145. Min Range: -3.5145

Max Act: 3.4205. Min Act: -0.1700

Data Index: 802980 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 3.5145. Min Range: -3.5145

Max Act: 3.4205. Min Act: -0.1700

Data Index: 302899 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 3.5145. Min Range: -3.5145

Max Act: 3.4048. Min Act: -0.1700

Data Index: 562276 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 3.5145. Min Range: -3.5145

Max Act: 3.4048. Min Act: -0.1700

Data Index: 234345 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 3.5145. Min Range: -3.5145

Max Act: 3.3891. Min Act: -0.1700

Data Index: 340115 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 3.5145. Min Range: -3.5145

Max Act: 3.3891. Min Act: -0.1700

Data Index: 220 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 3.5145. Min Range: -3.5145

Max Act: 3.4048. Min Act: -0.1700

Data Index: 829876 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 3.5145. Min Range: -3.5145

Max Act: 3.3891. Min Act: -0.1700

Data Index: 829685 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 3.5145. Min Range: -3.5145

Max Act: 3.4048. Min Act: -0.1700

Data Index: 696144 (C4 (Web Text))

Max Activating Token Index: 806