Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 931 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.5368. Min Act: -0.1700
Data Index: 658840 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.5368. Min Act: -0.1700
Data Index: 396965 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4721. Min Act: -0.1700
Data Index: 22686 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4883. Min Act: -0.1700
Data Index: 699500 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4883. Min Act: -0.1700
Data Index: 1347765 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4883. Min Act: -0.1700
Data Index: 43768 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4721. Min Act: -0.1700
Data Index: 773653 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4721. Min Act: -0.1700
Data Index: 443059 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4721. Min Act: -0.1700
Data Index: 867060 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4883. Min Act: -0.1700
Data Index: 14107 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4883. Min Act: -0.1700
Data Index: 976646 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4721. Min Act: -0.1700
Data Index: 749471 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4721. Min Act: -0.1700
Data Index: 1302463 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4559. Min Act: -0.1700
Data Index: 85797 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4559. Min Act: -0.1700
Data Index: 475504 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4721. Min Act: -0.1700
Data Index: 929294 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4721. Min Act: -0.1700
Data Index: 484192 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4721. Min Act: -0.1700
Data Index: 1032865 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4559. Min Act: -0.1700
Data Index: 426925 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4396. Min Act: -0.1700
Data Index: 286962 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19