Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2029 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 6.3408. Min Range: -6.3408
Max Act: 6.2158. Min Act: -0.1700
Data Index: 1317281 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3408. Min Range: -6.3408
Max Act: 6.3408. Min Act: -0.1700
Data Index: 1245730 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3408. Min Range: -6.3408
Max Act: 6.0596. Min Act: -0.1700
Data Index: 1047300 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3408. Min Range: -6.3408
Max Act: 6.0596. Min Act: -0.1700
Data Index: 290699 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3408. Min Range: -6.3408
Max Act: 6.0908. Min Act: -0.1700
Data Index: 1133538 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3408. Min Range: -6.3408
Max Act: 6.0283. Min Act: -0.1700
Data Index: 220696 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3408. Min Range: -6.3408
Max Act: 5.9658. Min Act: -0.1699
Data Index: 213211 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3408. Min Range: -6.3408
Max Act: 6.0283. Min Act: -0.1700
Data Index: 405852 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3408. Min Range: -6.3408
Max Act: 5.9658. Min Act: -0.1700
Data Index: 555675 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3408. Min Range: -6.3408
Max Act: 5.9658. Min Act: -0.1700
Data Index: 763267 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3408. Min Range: -6.3408
Max Act: 5.9658. Min Act: -0.1698
Data Index: 831622 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3408. Min Range: -6.3408
Max Act: 5.9033. Min Act: -0.1700
Data Index: 839882 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3408. Min Range: -6.3408
Max Act: 5.8721. Min Act: -0.1699
Data Index: 513543 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3408. Min Range: -6.3408
Max Act: 5.8096. Min Act: -0.1700
Data Index: 217995 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3408. Min Range: -6.3408
Max Act: 5.8408. Min Act: -0.1700
Data Index: 1292637 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3408. Min Range: -6.3408
Max Act: 5.8096. Min Act: -0.1700
Data Index: 1014488 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3408. Min Range: -6.3408
Max Act: 5.8408. Min Act: -0.1700
Data Index: 93123 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3408. Min Range: -6.3408
Max Act: 5.8096. Min Act: -0.1700
Data Index: 216137 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3408. Min Range: -6.3408
Max Act: 5.7783. Min Act: -0.1700
Data Index: 459331 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3408. Min Range: -6.3408
Max Act: 5.8096. Min Act: -0.1699
Data Index: 664318 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19