Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 282 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.5830. Min Range: -5.5830
Max Act: 5.5830. Min Act: -0.1700
Data Index: 724038 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5830. Min Range: -5.5830
Max Act: 5.4580. Min Act: -0.1700
Data Index: 1040496 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5830. Min Range: -5.5830
Max Act: 4.9268. Min Act: -0.1700
Data Index: 455144 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5830. Min Range: -5.5830
Max Act: 4.8955. Min Act: -0.1700
Data Index: 237207 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5830. Min Range: -5.5830
Max Act: 4.9580. Min Act: -0.1700
Data Index: 1176514 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5830. Min Range: -5.5830
Max Act: 4.9268. Min Act: -0.1700
Data Index: 643080 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5830. Min Range: -5.5830
Max Act: 4.8955. Min Act: -0.1700
Data Index: 377018 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5830. Min Range: -5.5830
Max Act: 4.8643. Min Act: -0.1700
Data Index: 1307483 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5830. Min Range: -5.5830
Max Act: 4.8643. Min Act: -0.1700
Data Index: 47078 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5830. Min Range: -5.5830
Max Act: 4.8330. Min Act: -0.1700
Data Index: 858154 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5830. Min Range: -5.5830
Max Act: 4.8018. Min Act: -0.1700
Data Index: 916079 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5830. Min Range: -5.5830
Max Act: 4.8330. Min Act: -0.1700
Data Index: 1459 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5830. Min Range: -5.5830
Max Act: 4.7393. Min Act: -0.1700
Data Index: 752145 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5830. Min Range: -5.5830
Max Act: 4.7393. Min Act: -0.1700
Data Index: 884988 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5830. Min Range: -5.5830
Max Act: 4.7705. Min Act: -0.1700
Data Index: 508939 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5830. Min Range: -5.5830
Max Act: 4.7705. Min Act: -0.1700
Data Index: 1252440 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5830. Min Range: -5.5830
Max Act: 4.7705. Min Act: -0.1700
Data Index: 104461 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5830. Min Range: -5.5830
Max Act: 4.7705. Min Act: -0.1700
Data Index: 632307 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5830. Min Range: -5.5830
Max Act: 4.8018. Min Act: -0.1700
Data Index: 23840 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5830. Min Range: -5.5830
Max Act: 4.6768. Min Act: -0.1700
Data Index: 570476 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19