Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1992 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.1555. Min Range: -3.1555
Max Act: 3.1555. Min Act: -0.1700
Data Index: 1018990 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1555. Min Range: -3.1555
Max Act: 3.0294. Min Act: -0.1700
Data Index: 81234 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1555. Min Range: -3.1555
Max Act: 3.0294. Min Act: -0.1700
Data Index: 764901 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1555. Min Range: -3.1555
Max Act: 3.0294. Min Act: -0.1700
Data Index: 375134 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1555. Min Range: -3.1555
Max Act: 3.0294. Min Act: -0.1700
Data Index: 748712 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1555. Min Range: -3.1555
Max Act: 2.9977. Min Act: -0.1700
Data Index: 151447 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1555. Min Range: -3.1555
Max Act: 3.0294. Min Act: -0.1700
Data Index: 932533 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1555. Min Range: -3.1555
Max Act: 3.0136. Min Act: -0.1700
Data Index: 864425 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1555. Min Range: -3.1555
Max Act: 2.9661. Min Act: -0.1700
Data Index: 476103 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1555. Min Range: -3.1555
Max Act: 2.9977. Min Act: -0.1700
Data Index: 779988 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1555. Min Range: -3.1555
Max Act: 2.9819. Min Act: -0.1700
Data Index: 1055888 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1555. Min Range: -3.1555
Max Act: 2.9819. Min Act: -0.1700
Data Index: 1454930 (Python Code)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1555. Min Range: -3.1555
Max Act: 2.9661. Min Act: -0.1700
Data Index: 114079 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1555. Min Range: -3.1555
Max Act: 3.0136. Min Act: -0.1700
Data Index: 440892 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1555. Min Range: -3.1555
Max Act: 2.9661. Min Act: -0.1700
Data Index: 617638 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1555. Min Range: -3.1555
Max Act: 2.9344. Min Act: -0.1700
Data Index: 852646 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1555. Min Range: -3.1555
Max Act: 2.9977. Min Act: -0.1700
Data Index: 607368 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1555. Min Range: -3.1555
Max Act: 2.9186. Min Act: -0.1700
Data Index: 642682 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1555. Min Range: -3.1555
Max Act: 2.9977. Min Act: -0.1700
Data Index: 941645 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1555. Min Range: -3.1555
Max Act: 2.9819. Min Act: -0.1700
Data Index: 954637 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19