Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1979 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6474. Min Range: -2.6474
Max Act: 2.6474. Min Act: -0.1700
Data Index: 891940 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6474. Min Range: -2.6474
Max Act: 2.6314. Min Act: -0.1700
Data Index: 1450822 (Python Code)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6474. Min Range: -2.6474
Max Act: 2.5992. Min Act: -0.1700
Data Index: 1542162 (Python Code)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6474. Min Range: -2.6474
Max Act: 2.5831. Min Act: -0.1700
Data Index: 1548519 (Python Code)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6474. Min Range: -2.6474
Max Act: 2.5831. Min Act: -0.1700
Data Index: 1591993 (Python Code)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6474. Min Range: -2.6474
Max Act: 2.5831. Min Act: -0.1700
Data Index: 1590779 (Python Code)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6474. Min Range: -2.6474
Max Act: 2.5831. Min Act: -0.1700
Data Index: 1602791 (Python Code)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6474. Min Range: -2.6474
Max Act: 2.5670. Min Act: -0.1700
Data Index: 1387803 (Python Code)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6474. Min Range: -2.6474
Max Act: 2.5831. Min Act: -0.1700
Data Index: 1500412 (Python Code)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6474. Min Range: -2.6474
Max Act: 2.5670. Min Act: -0.1700
Data Index: 1587242 (Python Code)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6474. Min Range: -2.6474
Max Act: 2.5670. Min Act: -0.1700
Data Index: 1409572 (Python Code)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6474. Min Range: -2.6474
Max Act: 2.5509. Min Act: -0.1700
Data Index: 1393290 (Python Code)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6474. Min Range: -2.6474
Max Act: 2.5670. Min Act: -0.1700
Data Index: 1554609 (Python Code)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6474. Min Range: -2.6474
Max Act: 2.5670. Min Act: -0.1700
Data Index: 1629192 (Python Code)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6474. Min Range: -2.6474
Max Act: 2.5670. Min Act: -0.1700
Data Index: 1511818 (Python Code)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6474. Min Range: -2.6474
Max Act: 2.5670. Min Act: -0.1700
Data Index: 1501039 (Python Code)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6474. Min Range: -2.6474
Max Act: 2.5831. Min Act: -0.1700
Data Index: 1609321 (Python Code)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6474. Min Range: -2.6474
Max Act: 2.5670. Min Act: -0.1700
Data Index: 1539243 (Python Code)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6474. Min Range: -2.6474
Max Act: 2.5509. Min Act: -0.1700
Data Index: 1600443 (Python Code)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6474. Min Range: -2.6474
Max Act: 2.5509. Min Act: -0.1700
Data Index: 1573193 (Python Code)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19