Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 840 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0269. Min Range: -4.0269
Max Act: 3.9956. Min Act: -0.1700
Data Index: 869531 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0269. Min Range: -4.0269
Max Act: 4.0269. Min Act: -0.1700
Data Index: 343055 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0269. Min Range: -4.0269
Max Act: 3.9643. Min Act: -0.1700
Data Index: 316067 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0269. Min Range: -4.0269
Max Act: 3.9018. Min Act: -0.1700
Data Index: 304741 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0269. Min Range: -4.0269
Max Act: 3.9331. Min Act: -0.1700
Data Index: 791381 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0269. Min Range: -4.0269
Max Act: 3.9331. Min Act: -0.1700
Data Index: 619739 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0269. Min Range: -4.0269
Max Act: 3.8705. Min Act: -0.1700
Data Index: 1214972 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0269. Min Range: -4.0269
Max Act: 3.9018. Min Act: -0.1700
Data Index: 659578 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0269. Min Range: -4.0269
Max Act: 3.8705. Min Act: -0.1700
Data Index: 768973 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0269. Min Range: -4.0269
Max Act: 3.8705. Min Act: -0.1700
Data Index: 111773 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0269. Min Range: -4.0269
Max Act: 3.9018. Min Act: -0.1700
Data Index: 677673 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0269. Min Range: -4.0269
Max Act: 3.8392. Min Act: -0.1700
Data Index: 251158 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0269. Min Range: -4.0269
Max Act: 3.8392. Min Act: -0.1700
Data Index: 1053564 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0269. Min Range: -4.0269
Max Act: 3.8392. Min Act: -0.1700
Data Index: 117346 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0269. Min Range: -4.0269
Max Act: 3.8080. Min Act: -0.1700
Data Index: 859539 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0269. Min Range: -4.0269
Max Act: 3.7767. Min Act: -0.1700
Data Index: 1140967 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0269. Min Range: -4.0269
Max Act: 3.7767. Min Act: -0.1700
Data Index: 544591 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0269. Min Range: -4.0269
Max Act: 3.7454. Min Act: -0.1700
Data Index: 1234399 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0269. Min Range: -4.0269
Max Act: 3.8080. Min Act: -0.1700
Data Index: 1028309 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0269. Min Range: -4.0269
Max Act: 3.7767. Min Act: -0.1700
Data Index: 319197 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19