Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 952 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.3893. Min Range: -2.3893
Max Act: 2.3893. Min Act: -0.1700
Data Index: 1256964 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3893. Min Range: -2.3893
Max Act: 2.3730. Min Act: -0.1700
Data Index: 1530555 (Python Code)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3893. Min Range: -2.3893
Max Act: 2.3730. Min Act: -0.1699
Data Index: 986731 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3893. Min Range: -2.3893
Max Act: 2.3566. Min Act: -0.1700
Data Index: 1497398 (Python Code)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3893. Min Range: -2.3893
Max Act: 2.3566. Min Act: -0.1699
Data Index: 89506 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3893. Min Range: -2.3893
Max Act: 2.3403. Min Act: -0.1700
Data Index: 1507895 (Python Code)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3893. Min Range: -2.3893
Max Act: 2.3239. Min Act: -0.1700
Data Index: 1655065 (Python Code)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3893. Min Range: -2.3893
Max Act: 2.3566. Min Act: -0.1700
Data Index: 1547818 (Python Code)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3893. Min Range: -2.3893
Max Act: 2.3403. Min Act: -0.1700
Data Index: 1364972 (Python Code)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3893. Min Range: -2.3893
Max Act: 2.3403. Min Act: -0.1700
Data Index: 182979 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3893. Min Range: -2.3893
Max Act: 2.3075. Min Act: -0.1700
Data Index: 196645 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3893. Min Range: -2.3893
Max Act: 2.3239. Min Act: -0.1700
Data Index: 1536973 (Python Code)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3893. Min Range: -2.3893
Max Act: 2.3239. Min Act: -0.1700
Data Index: 1447158 (Python Code)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3893. Min Range: -2.3893
Max Act: 2.3239. Min Act: -0.1700
Data Index: 237828 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3893. Min Range: -2.3893
Max Act: 2.3075. Min Act: -0.1700
Data Index: 361410 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3893. Min Range: -2.3893
Max Act: 2.2910. Min Act: -0.1700
Data Index: 1484179 (Python Code)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3893. Min Range: -2.3893
Max Act: 2.2745. Min Act: -0.1700
Data Index: 1452865 (Python Code)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3893. Min Range: -2.3893
Max Act: 2.2910. Min Act: -0.1700
Data Index: 1642768 (Python Code)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3893. Min Range: -2.3893
Max Act: 2.2910. Min Act: -0.1700
Data Index: 261215 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3893. Min Range: -2.3893
Max Act: 2.2745. Min Act: -0.1700
Data Index: 72968 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19