Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 354 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.6065. Min Range: -4.6065
Max Act: 4.6065. Min Act: -0.1700
Data Index: 101425 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6065. Min Range: -4.6065
Max Act: 4.5440. Min Act: -0.1700
Data Index: 1240912 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6065. Min Range: -4.6065
Max Act: 4.5753. Min Act: -0.1700
Data Index: 694746 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6065. Min Range: -4.6065
Max Act: 4.5440. Min Act: -0.1700
Data Index: 74877 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6065. Min Range: -4.6065
Max Act: 4.5440. Min Act: -0.1700
Data Index: 1036848 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6065. Min Range: -4.6065
Max Act: 4.4815. Min Act: -0.1700
Data Index: 697362 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6065. Min Range: -4.6065
Max Act: 4.5128. Min Act: -0.1700
Data Index: 489231 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6065. Min Range: -4.6065
Max Act: 4.5128. Min Act: -0.1700
Data Index: 690048 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6065. Min Range: -4.6065
Max Act: 4.4503. Min Act: -0.1700
Data Index: 173447 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6065. Min Range: -4.6065
Max Act: 4.4815. Min Act: -0.1700
Data Index: 1053642 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6065. Min Range: -4.6065
Max Act: 4.4190. Min Act: -0.1700
Data Index: 1220210 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6065. Min Range: -4.6065
Max Act: 4.4815. Min Act: -0.1699
Data Index: 316317 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6065. Min Range: -4.6065
Max Act: 4.3878. Min Act: -0.1700
Data Index: 1126309 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6065. Min Range: -4.6065
Max Act: 4.3878. Min Act: -0.1700
Data Index: 76224 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6065. Min Range: -4.6065
Max Act: 4.3565. Min Act: -0.1700
Data Index: 51754 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6065. Min Range: -4.6065
Max Act: 4.4190. Min Act: -0.1700
Data Index: 594760 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6065. Min Range: -4.6065
Max Act: 4.3253. Min Act: -0.1700
Data Index: 85215 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6065. Min Range: -4.6065
Max Act: 4.3253. Min Act: -0.1700
Data Index: 557952 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6065. Min Range: -4.6065
Max Act: 4.3878. Min Act: -0.1700
Data Index: 581520 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6065. Min Range: -4.6065
Max Act: 4.3253. Min Act: -0.1700
Data Index: 1048793 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19