Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 52 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.1280. Min Range: -3.1280
Max Act: 3.1280. Min Act: -0.1700
Data Index: 462880 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1280. Min Range: -3.1280
Max Act: 3.0807. Min Act: -0.1700
Data Index: 1090862 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1280. Min Range: -3.1280
Max Act: 3.0491. Min Act: -0.1700
Data Index: 976169 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1280. Min Range: -3.1280
Max Act: 3.0491. Min Act: -0.1700
Data Index: 363783 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1280. Min Range: -3.1280
Max Act: 3.0491. Min Act: -0.1700
Data Index: 1139725 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1280. Min Range: -3.1280
Max Act: 2.9859. Min Act: -0.1700
Data Index: 734175 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1280. Min Range: -3.1280
Max Act: 2.9384. Min Act: -0.1700
Data Index: 1353715 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1280. Min Range: -3.1280
Max Act: 2.9701. Min Act: -0.1700
Data Index: 1180620 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1280. Min Range: -3.1280
Max Act: 2.9542. Min Act: -0.1700
Data Index: 1096169 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1280. Min Range: -3.1280
Max Act: 3.0017. Min Act: -0.1700
Data Index: 298792 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1280. Min Range: -3.1280
Max Act: 2.9859. Min Act: -0.1700
Data Index: 741074 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1280. Min Range: -3.1280
Max Act: 2.9226. Min Act: -0.1700
Data Index: 1105836 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1280. Min Range: -3.1280
Max Act: 2.9384. Min Act: -0.1700
Data Index: 443836 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1280. Min Range: -3.1280
Max Act: 2.9384. Min Act: -0.1700
Data Index: 988909 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1280. Min Range: -3.1280
Max Act: 2.9384. Min Act: -0.1700
Data Index: 1012491 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1280. Min Range: -3.1280
Max Act: 2.8908. Min Act: -0.1700
Data Index: 862016 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1280. Min Range: -3.1280
Max Act: 2.8591. Min Act: -0.1700
Data Index: 435196 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1280. Min Range: -3.1280
Max Act: 2.8591. Min Act: -0.1700
Data Index: 451668 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1280. Min Range: -3.1280
Max Act: 2.8908. Min Act: -0.1700
Data Index: 52996 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1280. Min Range: -3.1280
Max Act: 2.9226. Min Act: -0.1700
Data Index: 509402 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19