Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 953 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2688. Min Range: -4.2688
Max Act: 4.2688. Min Act: -0.1700
Data Index: 86586 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2688. Min Range: -4.2688
Max Act: 4.2063. Min Act: -0.1700
Data Index: 386443 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2688. Min Range: -4.2688
Max Act: 4.2376. Min Act: -0.1700
Data Index: 858211 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2688. Min Range: -4.2688
Max Act: 4.2688. Min Act: -0.1700
Data Index: 1290424 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2688. Min Range: -4.2688
Max Act: 4.1751. Min Act: -0.1700
Data Index: 221771 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2688. Min Range: -4.2688
Max Act: 4.1126. Min Act: -0.1700
Data Index: 1481201 (Python Code)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2688. Min Range: -4.2688
Max Act: 4.1438. Min Act: -0.1700
Data Index: 1575941 (Python Code)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2688. Min Range: -4.2688
Max Act: 4.1438. Min Act: -0.1700
Data Index: 700814 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2688. Min Range: -4.2688
Max Act: 4.1438. Min Act: -0.1700
Data Index: 449176 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2688. Min Range: -4.2688
Max Act: 4.1126. Min Act: -0.1700
Data Index: 741141 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2688. Min Range: -4.2688
Max Act: 4.1751. Min Act: -0.1700
Data Index: 819043 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2688. Min Range: -4.2688
Max Act: 4.0813. Min Act: -0.1700
Data Index: 132222 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2688. Min Range: -4.2688
Max Act: 4.1438. Min Act: -0.1700
Data Index: 1422651 (Python Code)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2688. Min Range: -4.2688
Max Act: 4.1438. Min Act: -0.1700
Data Index: 1390334 (Python Code)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2688. Min Range: -4.2688
Max Act: 4.0813. Min Act: -0.1700
Data Index: 1420272 (Python Code)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2688. Min Range: -4.2688
Max Act: 4.1126. Min Act: -0.1700
Data Index: 1550381 (Python Code)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2688. Min Range: -4.2688
Max Act: 4.1126. Min Act: -0.1700
Data Index: 1517199 (Python Code)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2688. Min Range: -4.2688
Max Act: 4.1126. Min Act: -0.1700
Data Index: 1642518 (Python Code)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2688. Min Range: -4.2688
Max Act: 4.1126. Min Act: -0.1700
Data Index: 1622894 (Python Code)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2688. Min Range: -4.2688
Max Act: 4.0813. Min Act: -0.1700
Data Index: 111045 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19