Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 61 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.0813. Min Range: -4.0813
Max Act: 4.0813. Min Act: -0.1700
Data Index: 120008 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0813. Min Range: -4.0813
Max Act: 4.0501. Min Act: -0.1700
Data Index: 955928 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0813. Min Range: -4.0813
Max Act: 4.0813. Min Act: -0.1700
Data Index: 1586697 (Python Code)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0813. Min Range: -4.0813
Max Act: 4.0188. Min Act: -0.1700
Data Index: 494176 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0813. Min Range: -4.0813
Max Act: 3.9876. Min Act: -0.1700
Data Index: 1570707 (Python Code)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0813. Min Range: -4.0813
Max Act: 3.9876. Min Act: -0.1700
Data Index: 1612623 (Python Code)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0813. Min Range: -4.0813
Max Act: 3.9876. Min Act: -0.1700
Data Index: 57233 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0813. Min Range: -4.0813
Max Act: 3.9876. Min Act: -0.1700
Data Index: 540848 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0813. Min Range: -4.0813
Max Act: 3.9876. Min Act: -0.1700
Data Index: 1528700 (Python Code)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0813. Min Range: -4.0813
Max Act: 3.9563. Min Act: -0.1700
Data Index: 1469931 (Python Code)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0813. Min Range: -4.0813
Max Act: 3.9876. Min Act: -0.1700
Data Index: 1341668 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0813. Min Range: -4.0813
Max Act: 3.9563. Min Act: -0.1700
Data Index: 1053424 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0813. Min Range: -4.0813
Max Act: 3.9876. Min Act: -0.1700
Data Index: 1510144 (Python Code)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0813. Min Range: -4.0813
Max Act: 3.9250. Min Act: -0.1700
Data Index: 1499603 (Python Code)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0813. Min Range: -4.0813
Max Act: 3.9563. Min Act: -0.1700
Data Index: 1600670 (Python Code)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0813. Min Range: -4.0813
Max Act: 3.9250. Min Act: -0.1700
Data Index: 1488399 (Python Code)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0813. Min Range: -4.0813
Max Act: 3.9563. Min Act: -0.1700
Data Index: 1376750 (Python Code)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0813. Min Range: -4.0813
Max Act: 3.9250. Min Act: -0.1700
Data Index: 990342 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0813. Min Range: -4.0813
Max Act: 3.9563. Min Act: -0.1700
Data Index: 1346653 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0813. Min Range: -4.0813
Max Act: 3.9563. Min Act: -0.1700
Data Index: 860838 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19