Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1606 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.1344. Min Range: -3.1344
Max Act: 3.1344. Min Act: -0.1700
Data Index: 1450791 (Python Code)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1344. Min Range: -3.1344
Max Act: 3.0082. Min Act: -0.1700
Data Index: 970114 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1344. Min Range: -3.1344
Max Act: 3.0082. Min Act: -0.1700
Data Index: 531332 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1344. Min Range: -3.1344
Max Act: 2.9766. Min Act: -0.1700
Data Index: 1302812 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1344. Min Range: -3.1344
Max Act: 2.9766. Min Act: -0.1700
Data Index: 346225 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1344. Min Range: -3.1344
Max Act: 2.9607. Min Act: -0.1700
Data Index: 1452920 (Python Code)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1344. Min Range: -3.1344
Max Act: 2.9607. Min Act: -0.1700
Data Index: 1538856 (Python Code)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1344. Min Range: -3.1344
Max Act: 2.9607. Min Act: -0.1700
Data Index: 1014273 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1344. Min Range: -3.1344
Max Act: 2.9607. Min Act: -0.1700
Data Index: 908274 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1344. Min Range: -3.1344
Max Act: 2.9607. Min Act: -0.1700
Data Index: 1054740 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1344. Min Range: -3.1344
Max Act: 2.9607. Min Act: -0.1700
Data Index: 1169904 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1344. Min Range: -3.1344
Max Act: 2.9291. Min Act: -0.1700
Data Index: 354552 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1344. Min Range: -3.1344
Max Act: 2.9449. Min Act: -0.1700
Data Index: 1235802 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1344. Min Range: -3.1344
Max Act: 2.9449. Min Act: -0.1700
Data Index: 314138 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1344. Min Range: -3.1344
Max Act: 2.9607. Min Act: -0.1700
Data Index: 988762 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1344. Min Range: -3.1344
Max Act: 2.9291. Min Act: -0.1700
Data Index: 499727 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1344. Min Range: -3.1344
Max Act: 2.9449. Min Act: -0.1700
Data Index: 800258 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1344. Min Range: -3.1344
Max Act: 2.9449. Min Act: -0.1700
Data Index: 583061 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1344. Min Range: -3.1344
Max Act: 2.9607. Min Act: -0.1700
Data Index: 929367 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1344. Min Range: -3.1344
Max Act: 2.9291. Min Act: -0.1700
Data Index: 55423 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19