Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 637 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8674. Min Range: -2.8674
Max Act: 2.8674. Min Act: -0.1700
Data Index: 111981 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8674. Min Range: -2.8674
Max Act: 2.6920. Min Act: -0.1696
Data Index: 1228774 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8674. Min Range: -2.8674
Max Act: 2.6760. Min Act: -0.1592
Data Index: 956698 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8674. Min Range: -2.8674
Max Act: 2.6439. Min Act: -0.1693
Data Index: 1550601 (Python Code)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8674. Min Range: -2.8674
Max Act: 2.6439. Min Act: -0.1651
Data Index: 1541712 (Python Code)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8674. Min Range: -2.8674
Max Act: 2.6599. Min Act: -0.1699
Data Index: 1507370 (Python Code)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8674. Min Range: -2.8674
Max Act: 2.6278. Min Act: -0.0488
Data Index: 1473837 (Python Code)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8674. Min Range: -2.8674
Max Act: 2.5957. Min Act: -0.1700
Data Index: 1366778 (Python Code)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8674. Min Range: -2.8674
Max Act: 2.6118. Min Act: -0.1699
Data Index: 1388670 (Python Code)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8674. Min Range: -2.8674
Max Act: 2.6118. Min Act: -0.1690
Data Index: 1409602 (Python Code)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8674. Min Range: -2.8674
Max Act: 2.6118. Min Act: -0.1700
Data Index: 301518 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8674. Min Range: -2.8674
Max Act: 2.6118. Min Act: -0.1700
Data Index: 775919 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8674. Min Range: -2.8674
Max Act: 2.6278. Min Act: -0.1700
Data Index: 1476150 (Python Code)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8674. Min Range: -2.8674
Max Act: 2.6118. Min Act: -0.1699
Data Index: 1417249 (Python Code)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8674. Min Range: -2.8674
Max Act: 2.5957. Min Act: -0.1691
Data Index: 1460408 (Python Code)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8674. Min Range: -2.8674
Max Act: 2.5957. Min Act: -0.1700
Data Index: 512936 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8674. Min Range: -2.8674
Max Act: 2.5957. Min Act: -0.1700
Data Index: 1604216 (Python Code)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8674. Min Range: -2.8674
Max Act: 2.5957. Min Act: -0.1699
Data Index: 1574129 (Python Code)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8674. Min Range: -2.8674
Max Act: 2.5957. Min Act: -0.1694
Data Index: 1607536 (Python Code)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8674. Min Range: -2.8674
Max Act: 2.5957. Min Act: -0.1700
Data Index: 1370395 (Python Code)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19