Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1966 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8704. Min Range: -2.8704
Max Act: 2.8704. Min Act: -0.1700
Data Index: 1507356 (Python Code)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8704. Min Range: -2.8704
Max Act: 2.8545. Min Act: -0.1700
Data Index: 991545 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8704. Min Range: -2.8704
Max Act: 2.8227. Min Act: -0.1700
Data Index: 1529781 (Python Code)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8704. Min Range: -2.8704
Max Act: 2.8227. Min Act: -0.1700
Data Index: 1480801 (Python Code)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8704. Min Range: -2.8704
Max Act: 2.8227. Min Act: -0.1700
Data Index: 1510262 (Python Code)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8704. Min Range: -2.8704
Max Act: 2.8386. Min Act: -0.1700
Data Index: 1593787 (Python Code)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8704. Min Range: -2.8704
Max Act: 2.8227. Min Act: -0.1700
Data Index: 1588150 (Python Code)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8704. Min Range: -2.8704
Max Act: 2.7909. Min Act: -0.1700
Data Index: 1624987 (Python Code)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8704. Min Range: -2.8704
Max Act: 2.8068. Min Act: -0.1700
Data Index: 1300915 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8704. Min Range: -2.8704
Max Act: 2.7909. Min Act: -0.1700
Data Index: 1361907 (Python Code)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8704. Min Range: -2.8704
Max Act: 2.7590. Min Act: -0.1700
Data Index: 1508449 (Python Code)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8704. Min Range: -2.8704
Max Act: 2.8068. Min Act: -0.1700
Data Index: 1520097 (Python Code)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8704. Min Range: -2.8704
Max Act: 2.7909. Min Act: -0.1700
Data Index: 1596432 (Python Code)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8704. Min Range: -2.8704
Max Act: 2.7909. Min Act: -0.1700
Data Index: 1558224 (Python Code)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8704. Min Range: -2.8704
Max Act: 2.8068. Min Act: -0.1700
Data Index: 1544058 (Python Code)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8704. Min Range: -2.8704
Max Act: 2.7749. Min Act: -0.1700
Data Index: 1497998 (Python Code)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8704. Min Range: -2.8704
Max Act: 2.7909. Min Act: -0.1700
Data Index: 1471744 (Python Code)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8704. Min Range: -2.8704
Max Act: 2.7749. Min Act: -0.1700
Data Index: 1412705 (Python Code)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8704. Min Range: -2.8704
Max Act: 2.7749. Min Act: -0.1700
Data Index: 1482458 (Python Code)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8704. Min Range: -2.8704
Max Act: 2.7749. Min Act: -0.1700
Data Index: 1447748 (Python Code)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19