Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 307 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8981. Min Range: -2.8981
Max Act: 2.8981. Min Act: -0.1700
Data Index: 1361853 (Python Code)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8981. Min Range: -2.8981
Max Act: 2.8505. Min Act: -0.1700
Data Index: 386607 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8981. Min Range: -2.8981
Max Act: 2.8822. Min Act: -0.1700
Data Index: 1460452 (Python Code)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8981. Min Range: -2.8981
Max Act: 2.8664. Min Act: -0.1700
Data Index: 297260 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8981. Min Range: -2.8981
Max Act: 2.7709. Min Act: -0.1700
Data Index: 890773 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8981. Min Range: -2.8981
Max Act: 2.7709. Min Act: -0.1700
Data Index: 1273721 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8981. Min Range: -2.8981
Max Act: 2.7709. Min Act: -0.1700
Data Index: 1598568 (Python Code)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8981. Min Range: -2.8981
Max Act: 2.7709. Min Act: -0.1700
Data Index: 442310 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8981. Min Range: -2.8981
Max Act: 2.7709. Min Act: -0.1700
Data Index: 20501 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8981. Min Range: -2.8981
Max Act: 2.7709. Min Act: -0.1700
Data Index: 160796 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8981. Min Range: -2.8981
Max Act: 2.7390. Min Act: -0.1700
Data Index: 1061176 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8981. Min Range: -2.8981
Max Act: 2.7230. Min Act: -0.1700
Data Index: 65949 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8981. Min Range: -2.8981
Max Act: 2.7070. Min Act: -0.1700
Data Index: 95384 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8981. Min Range: -2.8981
Max Act: 2.6910. Min Act: -0.1700
Data Index: 305998 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8981. Min Range: -2.8981
Max Act: 2.6910. Min Act: -0.1700
Data Index: 221463 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8981. Min Range: -2.8981
Max Act: 2.7070. Min Act: -0.1700
Data Index: 1590166 (Python Code)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8981. Min Range: -2.8981
Max Act: 2.6750. Min Act: -0.1700
Data Index: 1629861 (Python Code)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8981. Min Range: -2.8981
Max Act: 2.7070. Min Act: -0.1700
Data Index: 539030 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8981. Min Range: -2.8981
Max Act: 2.6910. Min Act: -0.1700
Data Index: 684928 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8981. Min Range: -2.8981
Max Act: 2.6589. Min Act: -0.1700
Data Index: 1049943 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19