Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2028 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6031. Min Range: -4.6031
Max Act: 4.6031. Min Act: -0.1700
Data Index: 553040 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6031. Min Range: -4.6031
Max Act: 4.5718. Min Act: -0.1700
Data Index: 488358 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6031. Min Range: -4.6031
Max Act: 4.4781. Min Act: -0.1700
Data Index: 492688 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6031. Min Range: -4.6031
Max Act: 4.4468. Min Act: -0.1700
Data Index: 1128452 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6031. Min Range: -4.6031
Max Act: 4.4156. Min Act: -0.1700
Data Index: 855609 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6031. Min Range: -4.6031
Max Act: 4.4156. Min Act: -0.1700
Data Index: 592820 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6031. Min Range: -4.6031
Max Act: 4.3843. Min Act: -0.1700
Data Index: 169604 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6031. Min Range: -4.6031
Max Act: 4.3531. Min Act: -0.1700
Data Index: 987305 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6031. Min Range: -4.6031
Max Act: 4.3843. Min Act: -0.1700
Data Index: 293594 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6031. Min Range: -4.6031
Max Act: 4.3843. Min Act: -0.1700
Data Index: 803464 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6031. Min Range: -4.6031
Max Act: 4.4156. Min Act: -0.1700
Data Index: 18227 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6031. Min Range: -4.6031
Max Act: 4.4156. Min Act: -0.1700
Data Index: 1054114 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6031. Min Range: -4.6031
Max Act: 4.4156. Min Act: -0.1700
Data Index: 502829 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6031. Min Range: -4.6031
Max Act: 4.3218. Min Act: -0.1700
Data Index: 1309263 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6031. Min Range: -4.6031
Max Act: 4.2906. Min Act: -0.1700
Data Index: 780332 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6031. Min Range: -4.6031
Max Act: 4.3531. Min Act: -0.1700
Data Index: 1310396 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6031. Min Range: -4.6031
Max Act: 4.3531. Min Act: -0.1700
Data Index: 286586 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6031. Min Range: -4.6031
Max Act: 4.3531. Min Act: -0.1700
Data Index: 744474 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6031. Min Range: -4.6031
Max Act: 4.2906. Min Act: -0.1700
Data Index: 1211433 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6031. Min Range: -4.6031
Max Act: 4.3218. Min Act: -0.1700
Data Index: 709895 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19