Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 201 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.2966. Min Range: -5.2966
Max Act: 5.2966. Min Act: -0.1700
Data Index: 1449054 (Python Code)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2966. Min Range: -5.2966
Max Act: 5.1716. Min Act: -0.1700
Data Index: 1537949 (Python Code)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2966. Min Range: -5.2966
Max Act: 5.1404. Min Act: -0.1700
Data Index: 1394511 (Python Code)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2966. Min Range: -5.2966
Max Act: 5.1716. Min Act: -0.1700
Data Index: 1581824 (Python Code)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2966. Min Range: -5.2966
Max Act: 5.0466. Min Act: -0.1700
Data Index: 1639132 (Python Code)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2966. Min Range: -5.2966
Max Act: 4.9841. Min Act: -0.1700
Data Index: 1631687 (Python Code)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2966. Min Range: -5.2966
Max Act: 4.8904. Min Act: -0.1700
Data Index: 1409007 (Python Code)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2966. Min Range: -5.2966
Max Act: 4.9841. Min Act: -0.1700
Data Index: 1467187 (Python Code)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2966. Min Range: -5.2966
Max Act: 4.9529. Min Act: -0.1700
Data Index: 1572441 (Python Code)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2966. Min Range: -5.2966
Max Act: 4.9529. Min Act: -0.1700
Data Index: 1612372 (Python Code)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2966. Min Range: -5.2966
Max Act: 4.9529. Min Act: -0.1700
Data Index: 1407594 (Python Code)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2966. Min Range: -5.2966
Max Act: 4.8904. Min Act: -0.1700
Data Index: 1648385 (Python Code)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2966. Min Range: -5.2966
Max Act: 4.9216. Min Act: -0.1700
Data Index: 1379525 (Python Code)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2966. Min Range: -5.2966
Max Act: 4.8591. Min Act: -0.1700
Data Index: 1474680 (Python Code)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2966. Min Range: -5.2966
Max Act: 4.8591. Min Act: -0.1700
Data Index: 1643181 (Python Code)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2966. Min Range: -5.2966
Max Act: 4.9216. Min Act: -0.1700
Data Index: 1636506 (Python Code)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2966. Min Range: -5.2966
Max Act: 4.8591. Min Act: -0.1700
Data Index: 1552553 (Python Code)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2966. Min Range: -5.2966
Max Act: 4.9216. Min Act: -0.1700
Data Index: 1542301 (Python Code)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2966. Min Range: -5.2966
Max Act: 4.8279. Min Act: -0.1700
Data Index: 1595233 (Python Code)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2966. Min Range: -5.2966
Max Act: 4.8591. Min Act: -0.1700
Data Index: 1539007 (Python Code)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19