Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1177 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8348. Min Range: -2.8348
Max Act: 2.8348. Min Act: -0.1700
Data Index: 174539 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8348. Min Range: -2.8348
Max Act: 2.8348. Min Act: -0.1700
Data Index: 1080196 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8348. Min Range: -2.8348
Max Act: 2.7711. Min Act: -0.1700
Data Index: 176642 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8348. Min Range: -2.8348
Max Act: 2.7392. Min Act: -0.1700
Data Index: 221685 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8348. Min Range: -2.8348
Max Act: 2.7392. Min Act: -0.1700
Data Index: 473841 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8348. Min Range: -2.8348
Max Act: 2.7232. Min Act: -0.1700
Data Index: 940963 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8348. Min Range: -2.8348
Max Act: 2.7711. Min Act: -0.1700
Data Index: 972080 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8348. Min Range: -2.8348
Max Act: 2.7232. Min Act: -0.1700
Data Index: 815773 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8348. Min Range: -2.8348
Max Act: 2.7232. Min Act: -0.1700
Data Index: 697025 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8348. Min Range: -2.8348
Max Act: 2.6912. Min Act: -0.1700
Data Index: 332665 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8348. Min Range: -2.8348
Max Act: 2.6912. Min Act: -0.1700
Data Index: 99125 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8348. Min Range: -2.8348
Max Act: 2.7072. Min Act: -0.1700
Data Index: 12012 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8348. Min Range: -2.8348
Max Act: 2.6912. Min Act: -0.1700
Data Index: 420471 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8348. Min Range: -2.8348
Max Act: 2.6752. Min Act: -0.1700
Data Index: 545901 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8348. Min Range: -2.8348
Max Act: 2.6591. Min Act: -0.1700
Data Index: 269012 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8348. Min Range: -2.8348
Max Act: 2.6752. Min Act: -0.1700
Data Index: 5625 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8348. Min Range: -2.8348
Max Act: 2.6752. Min Act: -0.1700
Data Index: 373241 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8348. Min Range: -2.8348
Max Act: 2.6752. Min Act: -0.1700
Data Index: 944394 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8348. Min Range: -2.8348
Max Act: 2.6431. Min Act: -0.1700
Data Index: 713183 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8348. Min Range: -2.8348
Max Act: 2.6591. Min Act: -0.1700
Data Index: 951027 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19