Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 941 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.3746. Min Range: -2.3746
Max Act: 2.3746. Min Act: -0.1697
Data Index: 823822 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3746. Min Range: -2.3746
Max Act: 2.3583. Min Act: -0.1700
Data Index: 289816 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3746. Min Range: -2.3746
Max Act: 2.3419. Min Act: -0.1700
Data Index: 884344 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3746. Min Range: -2.3746
Max Act: 2.3091. Min Act: -0.1700
Data Index: 1039630 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3746. Min Range: -2.3746
Max Act: 2.2926. Min Act: -0.1698
Data Index: 476883 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3746. Min Range: -2.3746
Max Act: 2.2926. Min Act: -0.1699
Data Index: 802346 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3746. Min Range: -2.3746
Max Act: 2.2762. Min Act: -0.1700
Data Index: 62385 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3746. Min Range: -2.3746
Max Act: 2.3091. Min Act: -0.1695
Data Index: 514722 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3746. Min Range: -2.3746
Max Act: 2.2762. Min Act: -0.1700
Data Index: 936551 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3746. Min Range: -2.3746
Max Act: 2.2597. Min Act: -0.1700
Data Index: 620115 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3746. Min Range: -2.3746
Max Act: 2.2762. Min Act: -0.1700
Data Index: 851718 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3746. Min Range: -2.3746
Max Act: 2.2432. Min Act: -0.1700
Data Index: 309281 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3746. Min Range: -2.3746
Max Act: 2.2432. Min Act: -0.1700
Data Index: 1253560 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3746. Min Range: -2.3746
Max Act: 2.2597. Min Act: -0.1700
Data Index: 518535 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3746. Min Range: -2.3746
Max Act: 2.2432. Min Act: -0.1700
Data Index: 776141 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3746. Min Range: -2.3746
Max Act: 2.2267. Min Act: -0.1700
Data Index: 98132 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3746. Min Range: -2.3746
Max Act: 2.2267. Min Act: -0.1699
Data Index: 1173673 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3746. Min Range: -2.3746
Max Act: 2.2432. Min Act: -0.1698
Data Index: 914332 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3746. Min Range: -2.3746
Max Act: 2.2267. Min Act: -0.1700
Data Index: 517313 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3746. Min Range: -2.3746
Max Act: 2.2267. Min Act: -0.1700
Data Index: 929335 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19