Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2014 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7894. Min Range: -2.7894
Max Act: 2.7894. Min Act: -0.1700
Data Index: 260441 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7894. Min Range: -2.7894
Max Act: 2.7575. Min Act: -0.1700
Data Index: 455173 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7894. Min Range: -2.7894
Max Act: 2.7575. Min Act: -0.1700
Data Index: 393078 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7894. Min Range: -2.7894
Max Act: 2.7575. Min Act: -0.1700
Data Index: 67903 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7894. Min Range: -2.7894
Max Act: 2.7575. Min Act: -0.1700
Data Index: 130747 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7894. Min Range: -2.7894
Max Act: 2.7096. Min Act: -0.1700
Data Index: 370395 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7894. Min Range: -2.7894
Max Act: 2.7256. Min Act: -0.1700
Data Index: 429739 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7894. Min Range: -2.7894
Max Act: 2.7256. Min Act: -0.1700
Data Index: 465744 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7894. Min Range: -2.7894
Max Act: 2.7096. Min Act: -0.1700
Data Index: 871467 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7894. Min Range: -2.7894
Max Act: 2.7256. Min Act: -0.1700
Data Index: 1114169 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7894. Min Range: -2.7894
Max Act: 2.7416. Min Act: -0.1700
Data Index: 624477 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7894. Min Range: -2.7894
Max Act: 2.7096. Min Act: -0.1700
Data Index: 764716 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7894. Min Range: -2.7894
Max Act: 2.7096. Min Act: -0.1700
Data Index: 1076499 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7894. Min Range: -2.7894
Max Act: 2.6936. Min Act: -0.1700
Data Index: 1012479 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7894. Min Range: -2.7894
Max Act: 2.7096. Min Act: -0.1700
Data Index: 533491 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7894. Min Range: -2.7894
Max Act: 2.6936. Min Act: -0.1700
Data Index: 1117063 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7894. Min Range: -2.7894
Max Act: 2.6936. Min Act: -0.1700
Data Index: 18378 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7894. Min Range: -2.7894
Max Act: 2.6936. Min Act: -0.1700
Data Index: 1217796 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7894. Min Range: -2.7894
Max Act: 2.6936. Min Act: -0.1700
Data Index: 9971 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7894. Min Range: -2.7894
Max Act: 2.6776. Min Act: -0.1700
Data Index: 176552 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19