Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 498 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 5.0106. Min Range: -5.0106
Max Act: 5.0106. Min Act: -0.1700
Data Index: 572366 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0106. Min Range: -5.0106
Max Act: 4.6981. Min Act: -0.1700
Data Index: 647265 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0106. Min Range: -5.0106
Max Act: 4.5106. Min Act: -0.1700
Data Index: 1262999 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0106. Min Range: -5.0106
Max Act: 4.6044. Min Act: -0.1700
Data Index: 1214423 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0106. Min Range: -5.0106
Max Act: 4.5731. Min Act: -0.1700
Data Index: 1310634 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0106. Min Range: -5.0106
Max Act: 4.5106. Min Act: -0.1700
Data Index: 536157 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0106. Min Range: -5.0106
Max Act: 4.5419. Min Act: -0.1700
Data Index: 1148660 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0106. Min Range: -5.0106
Max Act: 4.5731. Min Act: -0.1700
Data Index: 561716 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0106. Min Range: -5.0106
Max Act: 4.4169. Min Act: -0.1700
Data Index: 747857 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0106. Min Range: -5.0106
Max Act: 4.4481. Min Act: -0.1700
Data Index: 1249591 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0106. Min Range: -5.0106
Max Act: 4.4169. Min Act: -0.1700
Data Index: 326951 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0106. Min Range: -5.0106
Max Act: 4.3856. Min Act: -0.1700
Data Index: 1207266 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0106. Min Range: -5.0106
Max Act: 4.4481. Min Act: -0.1700
Data Index: 1095954 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0106. Min Range: -5.0106
Max Act: 4.3544. Min Act: -0.1700
Data Index: 826690 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0106. Min Range: -5.0106
Max Act: 4.2918. Min Act: -0.1700
Data Index: 1313011 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0106. Min Range: -5.0106
Max Act: 4.3856. Min Act: -0.1700
Data Index: 806738 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0106. Min Range: -5.0106
Max Act: 4.3231. Min Act: -0.1700
Data Index: 1332158 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0106. Min Range: -5.0106
Max Act: 4.4481. Min Act: -0.1700
Data Index: 252590 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0106. Min Range: -5.0106
Max Act: 4.3544. Min Act: -0.1700
Data Index: 439154 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0106. Min Range: -5.0106
Max Act: 4.2918. Min Act: -0.1700
Data Index: 421110 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19