Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0094. Min Range: -4.0094
Max Act: 4.0094. Min Act: -0.1700
Data Index: 920642 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0094. Min Range: -4.0094
Max Act: 3.8530. Min Act: -0.1700
Data Index: 1342598 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0094. Min Range: -4.0094
Max Act: 3.6966. Min Act: -0.1700
Data Index: 1271336 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0094. Min Range: -4.0094
Max Act: 3.5244. Min Act: -0.1700
Data Index: 1349185 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0094. Min Range: -4.0094
Max Act: 3.6184. Min Act: -0.1700
Data Index: 654501 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0094. Min Range: -4.0094
Max Act: 3.5714. Min Act: -0.1700
Data Index: 1348915 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0094. Min Range: -4.0094
Max Act: 3.6184. Min Act: -0.1700
Data Index: 463905 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0094. Min Range: -4.0094
Max Act: 3.5714. Min Act: -0.1700
Data Index: 633725 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0094. Min Range: -4.0094
Max Act: 3.5870. Min Act: -0.1700
Data Index: 413330 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0094. Min Range: -4.0094
Max Act: 3.5870. Min Act: -0.1700
Data Index: 203245 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0094. Min Range: -4.0094
Max Act: 3.5714. Min Act: -0.1700
Data Index: 768422 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0094. Min Range: -4.0094
Max Act: 3.5401. Min Act: -0.1700
Data Index: 668760 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0094. Min Range: -4.0094
Max Act: 3.5714. Min Act: -0.1700
Data Index: 226537 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0094. Min Range: -4.0094
Max Act: 3.5401. Min Act: -0.1700
Data Index: 1231539 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0094. Min Range: -4.0094
Max Act: 3.5557. Min Act: -0.1700
Data Index: 1227051 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0094. Min Range: -4.0094
Max Act: 3.5401. Min Act: -0.1700
Data Index: 206098 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0094. Min Range: -4.0094
Max Act: 3.5401. Min Act: -0.1700
Data Index: 336181 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0094. Min Range: -4.0094
Max Act: 3.5401. Min Act: -0.1700
Data Index: 1262327 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0094. Min Range: -4.0094
Max Act: 3.5244. Min Act: -0.1700
Data Index: 547943 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0094. Min Range: -4.0094
Max Act: 3.5401. Min Act: -0.1700
Data Index: 287861 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19