Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2033 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.2208. Min Range: -4.2208
Max Act: 4.2208. Min Act: -0.1700
Data Index: 23456 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2208. Min Range: -4.2208
Max Act: 4.1895. Min Act: -0.1700
Data Index: 1197496 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2208. Min Range: -4.2208
Max Act: 4.1583. Min Act: -0.1700
Data Index: 731218 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2208. Min Range: -4.2208
Max Act: 4.1895. Min Act: -0.1700
Data Index: 403985 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2208. Min Range: -4.2208
Max Act: 4.1270. Min Act: -0.1700
Data Index: 724620 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2208. Min Range: -4.2208
Max Act: 4.1583. Min Act: -0.1700
Data Index: 752738 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2208. Min Range: -4.2208
Max Act: 4.1583. Min Act: -0.1700
Data Index: 27936 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2208. Min Range: -4.2208
Max Act: 4.1583. Min Act: -0.1700
Data Index: 949967 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2208. Min Range: -4.2208
Max Act: 4.1270. Min Act: -0.1700
Data Index: 1503799 (Python Code)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2208. Min Range: -4.2208
Max Act: 4.1270. Min Act: -0.1700
Data Index: 967179 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2208. Min Range: -4.2208
Max Act: 4.1270. Min Act: -0.1700
Data Index: 69066 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2208. Min Range: -4.2208
Max Act: 4.1583. Min Act: -0.1700
Data Index: 1315280 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2208. Min Range: -4.2208
Max Act: 4.0957. Min Act: -0.1700
Data Index: 1068904 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2208. Min Range: -4.2208
Max Act: 4.0645. Min Act: -0.1700
Data Index: 411008 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2208. Min Range: -4.2208
Max Act: 4.0957. Min Act: -0.1700
Data Index: 724846 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2208. Min Range: -4.2208
Max Act: 4.0957. Min Act: -0.1700
Data Index: 297747 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2208. Min Range: -4.2208
Max Act: 4.0645. Min Act: -0.1700
Data Index: 921570 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2208. Min Range: -4.2208
Max Act: 4.0332. Min Act: -0.1700
Data Index: 946269 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2208. Min Range: -4.2208
Max Act: 4.0957. Min Act: -0.1700
Data Index: 350386 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2208. Min Range: -4.2208
Max Act: 4.0957. Min Act: -0.1700
Data Index: 36952 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19