Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1189 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.9782. Min Act: -0.1700

Data Index: 818526 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.9001. Min Act: -0.1700

Data Index: 277656 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.8844. Min Act: -0.1700

Data Index: 813230 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.8844. Min Act: -0.1700

Data Index: 900168 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.8844. Min Act: -0.1700

Data Index: 503635 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.8688. Min Act: -0.1700

Data Index: 43115 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.8688. Min Act: -0.1700

Data Index: 489403 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.8062. Min Act: -0.1700

Data Index: 162062 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.7906. Min Act: -0.1700

Data Index: 33345 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.7906. Min Act: -0.1700

Data Index: 969989 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.7906. Min Act: -0.1700

Data Index: 47870 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.7593. Min Act: -0.1700

Data Index: 286821 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.7749. Min Act: -0.1700

Data Index: 102116 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.7437. Min Act: -0.1700

Data Index: 401239 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.7124. Min Act: -0.1700

Data Index: 1276122 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.7593. Min Act: -0.1700

Data Index: 1085254 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.6654. Min Act: -0.1700

Data Index: 518919 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.7124. Min Act: -0.1700

Data Index: 1095756 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.7280. Min Act: -0.1700

Data Index: 459217 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 3.9782. Min Range: -3.9782

Max Act: 3.7124. Min Act: -0.1700

Data Index: 608422 (C4 (Web Text))

Max Activating Token Index: 998