Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1992 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8829. Min Range: -2.8829
Max Act: 2.8829. Min Act: -0.1700
Data Index: 1504933 (Python Code)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8829. Min Range: -2.8829
Max Act: 2.8511. Min Act: -0.1700
Data Index: 1411548 (Python Code)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8829. Min Range: -2.8829
Max Act: 2.7875. Min Act: -0.1700
Data Index: 1428426 (Python Code)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8829. Min Range: -2.8829
Max Act: 2.4823. Min Act: -0.1700
Data Index: 1569640 (Python Code)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8829. Min Range: -2.8829
Max Act: 2.4172. Min Act: -0.1700
Data Index: 1055978 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8829. Min Range: -2.8829
Max Act: 2.3846. Min Act: -0.1700
Data Index: 1544717 (Python Code)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8829. Min Range: -2.8829
Max Act: 2.4009. Min Act: -0.1700
Data Index: 1590094 (Python Code)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8829. Min Range: -2.8829
Max Act: 2.3683. Min Act: -0.1700
Data Index: 710987 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8829. Min Range: -2.8829
Max Act: 2.3683. Min Act: -0.1700
Data Index: 1570600 (Python Code)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8829. Min Range: -2.8829
Max Act: 2.3519. Min Act: -0.1700
Data Index: 1450124 (Python Code)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8829. Min Range: -2.8829
Max Act: 2.3683. Min Act: -0.1700
Data Index: 1538529 (Python Code)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8829. Min Range: -2.8829
Max Act: 2.3519. Min Act: -0.1700
Data Index: 1583966 (Python Code)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8829. Min Range: -2.8829
Max Act: 2.3355. Min Act: -0.1700
Data Index: 1498838 (Python Code)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8829. Min Range: -2.8829
Max Act: 2.3683. Min Act: -0.1700
Data Index: 1447038 (Python Code)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8829. Min Range: -2.8829
Max Act: 2.3355. Min Act: -0.1700
Data Index: 13859 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8829. Min Range: -2.8829
Max Act: 2.3355. Min Act: -0.1700
Data Index: 1472876 (Python Code)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8829. Min Range: -2.8829
Max Act: 2.3519. Min Act: -0.1700
Data Index: 1519791 (Python Code)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8829. Min Range: -2.8829
Max Act: 2.3355. Min Act: -0.1700
Data Index: 1403734 (Python Code)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8829. Min Range: -2.8829
Max Act: 2.3191. Min Act: -0.1700
Data Index: 1622932 (Python Code)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8829. Min Range: -2.8829
Max Act: 2.3355. Min Act: -0.1700
Data Index: 759728 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19