Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1057 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.9430. Min Range: -6.9430
Max Act: 6.9430. Min Act: -0.1700
Data Index: 229689 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9430. Min Range: -6.9430
Max Act: 6.9430. Min Act: -0.1700
Data Index: 582275 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9430. Min Range: -6.9430
Max Act: 6.8180. Min Act: -0.1700
Data Index: 709290 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9430. Min Range: -6.9430
Max Act: 6.7868. Min Act: -0.1700
Data Index: 1267764 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9430. Min Range: -6.9430
Max Act: 6.7868. Min Act: -0.1700
Data Index: 465596 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9430. Min Range: -6.9430
Max Act: 6.6618. Min Act: -0.1700
Data Index: 968199 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9430. Min Range: -6.9430
Max Act: 6.6930. Min Act: -0.1700
Data Index: 1000241 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9430. Min Range: -6.9430
Max Act: 6.5993. Min Act: -0.1700
Data Index: 616351 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9430. Min Range: -6.9430
Max Act: 6.5993. Min Act: -0.1700
Data Index: 979095 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9430. Min Range: -6.9430
Max Act: 6.5368. Min Act: -0.1700
Data Index: 842023 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9430. Min Range: -6.9430
Max Act: 6.5993. Min Act: -0.1700
Data Index: 512866 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9430. Min Range: -6.9430
Max Act: 6.5368. Min Act: -0.1700
Data Index: 831732 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9430. Min Range: -6.9430
Max Act: 6.5368. Min Act: -0.1700
Data Index: 397925 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9430. Min Range: -6.9430
Max Act: 6.5368. Min Act: -0.1700
Data Index: 601827 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9430. Min Range: -6.9430
Max Act: 6.5368. Min Act: -0.1700
Data Index: 1185648 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9430. Min Range: -6.9430
Max Act: 6.5368. Min Act: -0.1700
Data Index: 1053781 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9430. Min Range: -6.9430
Max Act: 6.5055. Min Act: -0.1700
Data Index: 1127759 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9430. Min Range: -6.9430
Max Act: 6.5368. Min Act: -0.1700
Data Index: 262165 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9430. Min Range: -6.9430
Max Act: 6.5368. Min Act: -0.1700
Data Index: 104794 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9430. Min Range: -6.9430
Max Act: 6.4743. Min Act: -0.1699
Data Index: 764135 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19