Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 859 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2503. Min Range: -4.2503
Max Act: 4.1878. Min Act: -0.1700
Data Index: 97293 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2503. Min Range: -4.2503
Max Act: 4.2503. Min Act: -0.1700
Data Index: 203656 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2503. Min Range: -4.2503
Max Act: 4.1566. Min Act: -0.1700
Data Index: 806975 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2503. Min Range: -4.2503
Max Act: 4.0940. Min Act: -0.1700
Data Index: 1283629 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2503. Min Range: -4.2503
Max Act: 4.1253. Min Act: -0.1700
Data Index: 153099 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2503. Min Range: -4.2503
Max Act: 3.8908. Min Act: -0.1700
Data Index: 1355838 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2503. Min Range: -4.2503
Max Act: 3.9221. Min Act: -0.1700
Data Index: 968938 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2503. Min Range: -4.2503
Max Act: 3.8752. Min Act: -0.1700
Data Index: 377045 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2503. Min Range: -4.2503
Max Act: 3.9064. Min Act: -0.1700
Data Index: 1019690 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2503. Min Range: -4.2503
Max Act: 3.9064. Min Act: -0.1700
Data Index: 578447 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2503. Min Range: -4.2503
Max Act: 3.8595. Min Act: -0.1700
Data Index: 215955 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2503. Min Range: -4.2503
Max Act: 3.9064. Min Act: -0.1700
Data Index: 472998 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2503. Min Range: -4.2503
Max Act: 3.8595. Min Act: -0.1700
Data Index: 1210066 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2503. Min Range: -4.2503
Max Act: 3.8595. Min Act: -0.1700
Data Index: 2660 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2503. Min Range: -4.2503
Max Act: 3.7970. Min Act: -0.1700
Data Index: 875077 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2503. Min Range: -4.2503
Max Act: 3.7813. Min Act: -0.1700
Data Index: 1300449 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2503. Min Range: -4.2503
Max Act: 3.8439. Min Act: -0.1700
Data Index: 1140322 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2503. Min Range: -4.2503
Max Act: 3.8282. Min Act: -0.1700
Data Index: 219396 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2503. Min Range: -4.2503
Max Act: 3.7970. Min Act: -0.1700
Data Index: 1224050 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2503. Min Range: -4.2503
Max Act: 3.8282. Min Act: -0.1700
Data Index: 661117 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19