Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1024 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7960. Min Range: -2.7960
Max Act: 2.7960. Min Act: -0.1700
Data Index: 965792 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7960. Min Range: -2.7960
Max Act: 2.6681. Min Act: -0.1700
Data Index: 978343 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7960. Min Range: -2.7960
Max Act: 2.6681. Min Act: -0.1700
Data Index: 134407 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7960. Min Range: -2.7960
Max Act: 2.6681. Min Act: -0.1700
Data Index: 614573 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7960. Min Range: -2.7960
Max Act: 2.6681. Min Act: -0.1700
Data Index: 670885 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7960. Min Range: -2.7960
Max Act: 2.6521. Min Act: -0.1700
Data Index: 566542 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7960. Min Range: -2.7960
Max Act: 2.6521. Min Act: -0.1700
Data Index: 315121 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7960. Min Range: -2.7960
Max Act: 2.5878. Min Act: -0.1700
Data Index: 198219 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7960. Min Range: -2.7960
Max Act: 2.5878. Min Act: -0.1700
Data Index: 1097337 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7960. Min Range: -2.7960
Max Act: 2.5717. Min Act: -0.1700
Data Index: 1296161 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7960. Min Range: -2.7960
Max Act: 2.5878. Min Act: -0.1700
Data Index: 1228759 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7960. Min Range: -2.7960
Max Act: 2.5878. Min Act: -0.1700
Data Index: 1128166 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7960. Min Range: -2.7960
Max Act: 2.5717. Min Act: -0.1700
Data Index: 163615 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7960. Min Range: -2.7960
Max Act: 2.5556. Min Act: -0.1700
Data Index: 309385 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7960. Min Range: -2.7960
Max Act: 2.5556. Min Act: -0.1700
Data Index: 799629 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7960. Min Range: -2.7960
Max Act: 2.5556. Min Act: -0.1700
Data Index: 490914 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7960. Min Range: -2.7960
Max Act: 2.5556. Min Act: -0.1700
Data Index: 586821 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7960. Min Range: -2.7960
Max Act: 2.5556. Min Act: -0.1700
Data Index: 240763 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7960. Min Range: -2.7960
Max Act: 2.5717. Min Act: -0.1700
Data Index: 472155 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7960. Min Range: -2.7960
Max Act: 2.5556. Min Act: -0.1700
Data Index: 737674 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19