Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2034 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7333. Min Range: -2.7333
Max Act: 2.7333. Min Act: -0.1700
Data Index: 923839 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7333. Min Range: -2.7333
Max Act: 2.7173. Min Act: -0.1700
Data Index: 1352569 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7333. Min Range: -2.7333
Max Act: 2.6532. Min Act: -0.1700
Data Index: 1227807 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7333. Min Range: -2.7333
Max Act: 2.6692. Min Act: -0.1700
Data Index: 390257 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7333. Min Range: -2.7333
Max Act: 2.6211. Min Act: -0.1700
Data Index: 34620 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7333. Min Range: -2.7333
Max Act: 2.6372. Min Act: -0.1700
Data Index: 243924 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7333. Min Range: -2.7333
Max Act: 2.6692. Min Act: -0.1700
Data Index: 340024 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7333. Min Range: -2.7333
Max Act: 2.6372. Min Act: -0.1700
Data Index: 1262951 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7333. Min Range: -2.7333
Max Act: 2.6853. Min Act: -0.1700
Data Index: 693647 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7333. Min Range: -2.7333
Max Act: 2.6532. Min Act: -0.1700
Data Index: 669422 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7333. Min Range: -2.7333
Max Act: 2.6372. Min Act: -0.1700
Data Index: 1157240 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7333. Min Range: -2.7333
Max Act: 2.6211. Min Act: -0.1700
Data Index: 200067 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7333. Min Range: -2.7333
Max Act: 2.6372. Min Act: -0.1700
Data Index: 1448403 (Python Code)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7333. Min Range: -2.7333
Max Act: 2.6050. Min Act: -0.1700
Data Index: 620173 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7333. Min Range: -2.7333
Max Act: 2.6372. Min Act: -0.1700
Data Index: 858626 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7333. Min Range: -2.7333
Max Act: 2.5889. Min Act: -0.1700
Data Index: 913362 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7333. Min Range: -2.7333
Max Act: 2.6050. Min Act: -0.1700
Data Index: 1156953 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7333. Min Range: -2.7333
Max Act: 2.5889. Min Act: -0.1700
Data Index: 374502 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7333. Min Range: -2.7333
Max Act: 2.6211. Min Act: -0.1700
Data Index: 487966 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7333. Min Range: -2.7333
Max Act: 2.6211. Min Act: -0.1700
Data Index: 1632080 (Python Code)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19