Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1534 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.1603. Min Range: -5.1603
Max Act: 5.1603. Min Act: -0.1700
Data Index: 918918 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1603. Min Range: -5.1603
Max Act: 5.0978. Min Act: -0.1700
Data Index: 924180 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1603. Min Range: -5.1603
Max Act: 5.0978. Min Act: -0.1700
Data Index: 1218249 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1603. Min Range: -5.1603
Max Act: 5.0666. Min Act: -0.1700
Data Index: 902425 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1603. Min Range: -5.1603
Max Act: 5.0353. Min Act: -0.1700
Data Index: 625881 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1603. Min Range: -5.1603
Max Act: 5.0041. Min Act: -0.1700
Data Index: 963455 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1603. Min Range: -5.1603
Max Act: 5.0353. Min Act: -0.1700
Data Index: 819373 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1603. Min Range: -5.1603
Max Act: 5.0353. Min Act: -0.1700
Data Index: 1178261 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1603. Min Range: -5.1603
Max Act: 5.0353. Min Act: -0.1700
Data Index: 1053681 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1603. Min Range: -5.1603
Max Act: 4.9728. Min Act: -0.1700
Data Index: 993040 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1603. Min Range: -5.1603
Max Act: 4.9728. Min Act: -0.1700
Data Index: 529093 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1603. Min Range: -5.1603
Max Act: 4.9416. Min Act: -0.1700
Data Index: 712894 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1603. Min Range: -5.1603
Max Act: 4.9728. Min Act: -0.1700
Data Index: 1273817 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1603. Min Range: -5.1603
Max Act: 4.9728. Min Act: -0.1700
Data Index: 1182074 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1603. Min Range: -5.1603
Max Act: 4.9103. Min Act: -0.1700
Data Index: 914999 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1603. Min Range: -5.1603
Max Act: 4.9103. Min Act: -0.1700
Data Index: 1127421 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1603. Min Range: -5.1603
Max Act: 4.9728. Min Act: -0.1700
Data Index: 1123389 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1603. Min Range: -5.1603
Max Act: 4.9103. Min Act: -0.1700
Data Index: 1270496 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1603. Min Range: -5.1603
Max Act: 4.9103. Min Act: -0.1700
Data Index: 462613 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1603. Min Range: -5.1603
Max Act: 4.8791. Min Act: -0.1700
Data Index: 727386 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19