Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 213 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5536. Min Range: -2.5536
Max Act: 2.5536. Min Act: -0.1700
Data Index: 528487 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5536. Min Range: -2.5536
Max Act: 2.5213. Min Act: -0.1700
Data Index: 545341 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5536. Min Range: -2.5536
Max Act: 2.5052. Min Act: -0.1700
Data Index: 19873 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5536. Min Range: -2.5536
Max Act: 2.5052. Min Act: -0.1700
Data Index: 810696 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5536. Min Range: -2.5536
Max Act: 2.5052. Min Act: -0.1700
Data Index: 1220310 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5536. Min Range: -2.5536
Max Act: 2.4727. Min Act: -0.1700
Data Index: 763345 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5536. Min Range: -2.5536
Max Act: 2.4890. Min Act: -0.1700
Data Index: 1214601 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5536. Min Range: -2.5536
Max Act: 2.4403. Min Act: -0.1700
Data Index: 422940 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5536. Min Range: -2.5536
Max Act: 2.4565. Min Act: -0.1700
Data Index: 930854 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5536. Min Range: -2.5536
Max Act: 2.4565. Min Act: -0.1700
Data Index: 534907 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5536. Min Range: -2.5536
Max Act: 2.4240. Min Act: -0.1700
Data Index: 1514803 (Python Code)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5536. Min Range: -2.5536
Max Act: 2.4240. Min Act: -0.1700
Data Index: 1098671 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5536. Min Range: -2.5536
Max Act: 2.4240. Min Act: -0.1700
Data Index: 184978 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5536. Min Range: -2.5536
Max Act: 2.4403. Min Act: -0.1700
Data Index: 1196975 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5536. Min Range: -2.5536
Max Act: 2.4077. Min Act: -0.1700
Data Index: 245495 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5536. Min Range: -2.5536
Max Act: 2.4077. Min Act: -0.1700
Data Index: 193250 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5536. Min Range: -2.5536
Max Act: 2.3914. Min Act: -0.1700
Data Index: 1622795 (Python Code)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5536. Min Range: -2.5536
Max Act: 2.3914. Min Act: -0.1700
Data Index: 1635740 (Python Code)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5536. Min Range: -2.5536
Max Act: 2.3914. Min Act: -0.1700
Data Index: 424834 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5536. Min Range: -2.5536
Max Act: 2.4240. Min Act: -0.1700
Data Index: 993595 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19