Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 184 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.5027. Min Range: -4.5027
Max Act: 4.5027. Min Act: -0.1700
Data Index: 948854 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5027. Min Range: -4.5027
Max Act: 4.4715. Min Act: -0.1700
Data Index: 471985 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5027. Min Range: -4.5027
Max Act: 4.4090. Min Act: -0.1700
Data Index: 258317 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5027. Min Range: -4.5027
Max Act: 4.4090. Min Act: -0.1700
Data Index: 323837 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5027. Min Range: -4.5027
Max Act: 4.3152. Min Act: -0.1700
Data Index: 1188337 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5027. Min Range: -4.5027
Max Act: 4.3777. Min Act: -0.1700
Data Index: 847083 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5027. Min Range: -4.5027
Max Act: 4.3465. Min Act: -0.1700
Data Index: 1006318 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5027. Min Range: -4.5027
Max Act: 4.3152. Min Act: -0.1700
Data Index: 804063 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5027. Min Range: -4.5027
Max Act: 4.3152. Min Act: -0.1700
Data Index: 219285 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5027. Min Range: -4.5027
Max Act: 4.3152. Min Act: -0.1700
Data Index: 879883 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5027. Min Range: -4.5027
Max Act: 4.2840. Min Act: -0.1700
Data Index: 618359 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5027. Min Range: -4.5027
Max Act: 4.2840. Min Act: -0.1700
Data Index: 704961 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5027. Min Range: -4.5027
Max Act: 4.2527. Min Act: -0.1700
Data Index: 1266052 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5027. Min Range: -4.5027
Max Act: 4.2527. Min Act: -0.1700
Data Index: 397392 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5027. Min Range: -4.5027
Max Act: 4.2527. Min Act: -0.1700
Data Index: 951894 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5027. Min Range: -4.5027
Max Act: 4.2214. Min Act: -0.1700
Data Index: 921533 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5027. Min Range: -4.5027
Max Act: 4.2214. Min Act: -0.1700
Data Index: 270566 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5027. Min Range: -4.5027
Max Act: 4.2214. Min Act: -0.1700
Data Index: 860964 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5027. Min Range: -4.5027
Max Act: 4.1589. Min Act: -0.1700
Data Index: 868617 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5027. Min Range: -4.5027
Max Act: 4.1902. Min Act: -0.1700
Data Index: 636824 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19