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

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

Neuron 326 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: 3.8141. Min Range: -3.8141

Max Act: 3.8141. Min Act: -0.1700

Data Index: 1310933 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 3.8141. Min Range: -3.8141

Max Act: 3.7046. Min Act: -0.1700

Data Index: 272945 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 3.8141. Min Range: -3.8141

Max Act: 3.6890. Min Act: -0.1700

Data Index: 411395 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 3.8141. Min Range: -3.8141

Max Act: 3.7046. Min Act: -0.1700

Data Index: 454285 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 3.8141. Min Range: -3.8141

Max Act: 3.6577. Min Act: -0.1700

Data Index: 368262 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 3.8141. Min Range: -3.8141

Max Act: 3.6420. Min Act: -0.1700

Data Index: 1113427 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 3.8141. Min Range: -3.8141

Max Act: 3.6264. Min Act: -0.1700

Data Index: 1279665 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 3.8141. Min Range: -3.8141

Max Act: 3.5794. Min Act: -0.1700

Data Index: 43739 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 3.8141. Min Range: -3.8141

Max Act: 3.5324. Min Act: -0.1700

Data Index: 839202 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 3.8141. Min Range: -3.8141

Max Act: 3.5168. Min Act: -0.1700

Data Index: 86106 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 3.8141. Min Range: -3.8141

Max Act: 3.5011. Min Act: -0.1700

Data Index: 756057 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 3.8141. Min Range: -3.8141

Max Act: 3.5324. Min Act: -0.1700

Data Index: 258313 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 3.8141. Min Range: -3.8141

Max Act: 3.5324. Min Act: -0.1700

Data Index: 135789 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 3.8141. Min Range: -3.8141

Max Act: 3.5481. Min Act: -0.1700

Data Index: 726189 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 3.8141. Min Range: -3.8141

Max Act: 3.5168. Min Act: -0.1700

Data Index: 715704 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 3.8141. Min Range: -3.8141

Max Act: 3.5168. Min Act: -0.1700

Data Index: 291039 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 3.8141. Min Range: -3.8141

Max Act: 3.5324. Min Act: -0.1700

Data Index: 955814 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 3.8141. Min Range: -3.8141

Max Act: 3.5168. Min Act: -0.1700

Data Index: 233022 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 3.8141. Min Range: -3.8141

Max Act: 3.4854. Min Act: -0.1700

Data Index: 951506 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 3.8141. Min Range: -3.8141

Max Act: 3.4854. Min Act: -0.1700

Data Index: 253113 (C4 (Web Text))

Max Activating Token Index: 12