Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 783 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1540. Min Range: -4.1540
Max Act: 4.1540. Min Act: -0.1700
Data Index: 443076 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1540. Min Range: -4.1540
Max Act: 4.1227. Min Act: -0.1700
Data Index: 99124 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1540. Min Range: -4.1540
Max Act: 4.1227. Min Act: -0.1700
Data Index: 475568 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1540. Min Range: -4.1540
Max Act: 4.0289. Min Act: -0.1700
Data Index: 329181 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1540. Min Range: -4.1540
Max Act: 4.0602. Min Act: -0.1700
Data Index: 896674 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1540. Min Range: -4.1540
Max Act: 4.0915. Min Act: -0.1700
Data Index: 322718 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1540. Min Range: -4.1540
Max Act: 4.0915. Min Act: -0.1700
Data Index: 745434 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1540. Min Range: -4.1540
Max Act: 4.0289. Min Act: -0.1700
Data Index: 456701 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1540. Min Range: -4.1540
Max Act: 3.9977. Min Act: -0.1700
Data Index: 1037886 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1540. Min Range: -4.1540
Max Act: 3.9977. Min Act: -0.1700
Data Index: 915714 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1540. Min Range: -4.1540
Max Act: 3.9664. Min Act: -0.1700
Data Index: 396129 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1540. Min Range: -4.1540
Max Act: 3.9664. Min Act: -0.1700
Data Index: 694792 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1540. Min Range: -4.1540
Max Act: 3.9351. Min Act: -0.1700
Data Index: 828948 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1540. Min Range: -4.1540
Max Act: 3.9664. Min Act: -0.1700
Data Index: 335170 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1540. Min Range: -4.1540
Max Act: 3.9351. Min Act: -0.1700
Data Index: 90750 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1540. Min Range: -4.1540
Max Act: 3.9351. Min Act: -0.1700
Data Index: 1258020 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1540. Min Range: -4.1540
Max Act: 3.9351. Min Act: -0.1699
Data Index: 1292080 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1540. Min Range: -4.1540
Max Act: 3.9039. Min Act: -0.1700
Data Index: 1336169 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1540. Min Range: -4.1540
Max Act: 3.9351. Min Act: -0.1700
Data Index: 250256 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1540. Min Range: -4.1540
Max Act: 3.8413. Min Act: -0.1700
Data Index: 1158748 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19