Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 52 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.0985. Min Range: -3.0985
Max Act: 3.0985. Min Act: -0.1700
Data Index: 718919 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0985. Min Range: -3.0985
Max Act: 3.0985. Min Act: -0.1700
Data Index: 112447 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0985. Min Range: -3.0985
Max Act: 3.0669. Min Act: -0.1700
Data Index: 945515 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0985. Min Range: -3.0985
Max Act: 3.0511. Min Act: -0.1700
Data Index: 673100 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0985. Min Range: -3.0985
Max Act: 3.0195. Min Act: -0.1700
Data Index: 1079182 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0985. Min Range: -3.0985
Max Act: 3.0037. Min Act: -0.1700
Data Index: 916417 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0985. Min Range: -3.0985
Max Act: 3.0037. Min Act: -0.1700
Data Index: 995519 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0985. Min Range: -3.0985
Max Act: 2.9721. Min Act: -0.1700
Data Index: 178647 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0985. Min Range: -3.0985
Max Act: 2.9721. Min Act: -0.1700
Data Index: 432357 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0985. Min Range: -3.0985
Max Act: 2.9721. Min Act: -0.1700
Data Index: 941599 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0985. Min Range: -3.0985
Max Act: 2.9405. Min Act: -0.1700
Data Index: 216946 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0985. Min Range: -3.0985
Max Act: 2.9405. Min Act: -0.1700
Data Index: 338464 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0985. Min Range: -3.0985
Max Act: 2.9563. Min Act: -0.1700
Data Index: 608833 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0985. Min Range: -3.0985
Max Act: 2.9563. Min Act: -0.1700
Data Index: 637015 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0985. Min Range: -3.0985
Max Act: 2.9405. Min Act: -0.1700
Data Index: 1153184 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0985. Min Range: -3.0985
Max Act: 2.9405. Min Act: -0.1700
Data Index: 1090825 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0985. Min Range: -3.0985
Max Act: 2.9246. Min Act: -0.1700
Data Index: 873882 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0985. Min Range: -3.0985
Max Act: 2.9088. Min Act: -0.1700
Data Index: 910382 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0985. Min Range: -3.0985
Max Act: 2.9088. Min Act: -0.1700
Data Index: 446391 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0985. Min Range: -3.0985
Max Act: 2.9088. Min Act: -0.1700
Data Index: 457815 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19