Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1788 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 1.6863. Min Range: -1.6863
Max Act: 1.6863. Min Act: -0.1700
Data Index: 775735 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6863. Min Range: -1.6863
Max Act: 1.6776. Min Act: -0.1700
Data Index: 984372 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6863. Min Range: -1.6863
Max Act: 1.6776. Min Act: -0.1700
Data Index: 258014 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6863. Min Range: -1.6863
Max Act: 1.6776. Min Act: -0.1700
Data Index: 217953 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6863. Min Range: -1.6863
Max Act: 1.6690. Min Act: -0.1700
Data Index: 845397 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6863. Min Range: -1.6863
Max Act: 1.6690. Min Act: -0.1700
Data Index: 748991 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6863. Min Range: -1.6863
Max Act: 1.6776. Min Act: -0.1700
Data Index: 994582 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6863. Min Range: -1.6863
Max Act: 1.6690. Min Act: -0.1700
Data Index: 1081583 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6863. Min Range: -1.6863
Max Act: 1.6603. Min Act: -0.1700
Data Index: 219514 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6863. Min Range: -1.6863
Max Act: 1.6516. Min Act: -0.1700
Data Index: 1345921 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6863. Min Range: -1.6863
Max Act: 1.6516. Min Act: -0.1700
Data Index: 483338 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6863. Min Range: -1.6863
Max Act: 1.6342. Min Act: -0.1700
Data Index: 449993 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6863. Min Range: -1.6863
Max Act: 1.6342. Min Act: -0.1700
Data Index: 265030 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6863. Min Range: -1.6863
Max Act: 1.6255. Min Act: -0.1700
Data Index: 1122470 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6863. Min Range: -1.6863
Max Act: 1.6255. Min Act: -0.1700
Data Index: 831208 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6863. Min Range: -1.6863
Max Act: 1.6167. Min Act: -0.1700
Data Index: 1187878 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6863. Min Range: -1.6863
Max Act: 1.6255. Min Act: -0.1700
Data Index: 989694 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6863. Min Range: -1.6863
Max Act: 1.6167. Min Act: -0.1700
Data Index: 342275 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6863. Min Range: -1.6863
Max Act: 1.6080. Min Act: -0.1700
Data Index: 935206 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6863. Min Range: -1.6863
Max Act: 1.5818. Min Act: -0.1700
Data Index: 446967 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19