Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1436 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7630. Min Range: -4.7630
Max Act: 4.7630. Min Act: -0.1700
Data Index: 1254033 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7630. Min Range: -4.7630
Max Act: 4.6692. Min Act: -0.1700
Data Index: 1563770 (Python Code)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7630. Min Range: -4.7630
Max Act: 4.6692. Min Act: -0.1700
Data Index: 1056988 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7630. Min Range: -4.7630
Max Act: 4.5755. Min Act: -0.1700
Data Index: 1094339 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7630. Min Range: -4.7630
Max Act: 4.4505. Min Act: -0.1700
Data Index: 191763 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7630. Min Range: -4.7630
Max Act: 4.4505. Min Act: -0.1700
Data Index: 1454177 (Python Code)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7630. Min Range: -4.7630
Max Act: 4.5130. Min Act: -0.1700
Data Index: 944288 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7630. Min Range: -4.7630
Max Act: 4.5130. Min Act: -0.1700
Data Index: 960215 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7630. Min Range: -4.7630
Max Act: 4.4192. Min Act: -0.1700
Data Index: 895960 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7630. Min Range: -4.7630
Max Act: 4.4505. Min Act: -0.1700
Data Index: 1216245 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7630. Min Range: -4.7630
Max Act: 4.4192. Min Act: -0.1700
Data Index: 253667 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7630. Min Range: -4.7630
Max Act: 4.3880. Min Act: -0.1700
Data Index: 844611 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7630. Min Range: -4.7630
Max Act: 4.3880. Min Act: -0.1700
Data Index: 979275 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7630. Min Range: -4.7630
Max Act: 4.3880. Min Act: -0.1700
Data Index: 266345 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7630. Min Range: -4.7630
Max Act: 4.4192. Min Act: -0.1700
Data Index: 1285578 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7630. Min Range: -4.7630
Max Act: 4.3255. Min Act: -0.1700
Data Index: 9923 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7630. Min Range: -4.7630
Max Act: 4.3255. Min Act: -0.1700
Data Index: 144575 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7630. Min Range: -4.7630
Max Act: 4.3255. Min Act: -0.1700
Data Index: 288642 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7630. Min Range: -4.7630
Max Act: 4.3880. Min Act: -0.1700
Data Index: 1099026 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7630. Min Range: -4.7630
Max Act: 4.3880. Min Act: -0.1700
Data Index: 1338701 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19