Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 560 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.2677. Min Range: -4.2677
Max Act: 4.2677. Min Act: -0.1700
Data Index: 347943 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2677. Min Range: -4.2677
Max Act: 4.1739. Min Act: -0.1700
Data Index: 781933 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2677. Min Range: -4.2677
Max Act: 4.1114. Min Act: -0.1700
Data Index: 554947 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2677. Min Range: -4.2677
Max Act: 4.1114. Min Act: -0.1700
Data Index: 371377 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2677. Min Range: -4.2677
Max Act: 4.0801. Min Act: -0.1700
Data Index: 413703 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2677. Min Range: -4.2677
Max Act: 4.0488. Min Act: -0.1700
Data Index: 1107923 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2677. Min Range: -4.2677
Max Act: 4.0801. Min Act: -0.1700
Data Index: 559218 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2677. Min Range: -4.2677
Max Act: 4.0488. Min Act: -0.1700
Data Index: 54019 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2677. Min Range: -4.2677
Max Act: 4.0488. Min Act: -0.1700
Data Index: 1293749 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2677. Min Range: -4.2677
Max Act: 4.0488. Min Act: -0.1700
Data Index: 242791 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2677. Min Range: -4.2677
Max Act: 4.0801. Min Act: -0.1700
Data Index: 751822 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2677. Min Range: -4.2677
Max Act: 4.0488. Min Act: -0.1700
Data Index: 468455 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2677. Min Range: -4.2677
Max Act: 4.0488. Min Act: -0.1700
Data Index: 991775 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2677. Min Range: -4.2677
Max Act: 4.0176. Min Act: -0.1700
Data Index: 1268321 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2677. Min Range: -4.2677
Max Act: 4.0176. Min Act: -0.1700
Data Index: 827723 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2677. Min Range: -4.2677
Max Act: 3.9863. Min Act: -0.1700
Data Index: 4847 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2677. Min Range: -4.2677
Max Act: 4.0176. Min Act: -0.1700
Data Index: 804721 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2677. Min Range: -4.2677
Max Act: 3.9863. Min Act: -0.1700
Data Index: 1080773 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2677. Min Range: -4.2677
Max Act: 4.0176. Min Act: -0.1700
Data Index: 171696 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2677. Min Range: -4.2677
Max Act: 4.0176. Min Act: -0.1700
Data Index: 502584 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19