Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1982 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7763. Min Range: -2.7763
Max Act: 2.7763. Min Act: -0.1700
Data Index: 1430828 (Python Code)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7763. Min Range: -2.7763
Max Act: 2.7444. Min Act: -0.1700
Data Index: 1622139 (Python Code)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7763. Min Range: -2.7763
Max Act: 2.7444. Min Act: -0.1700
Data Index: 1542977 (Python Code)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7763. Min Range: -2.7763
Max Act: 2.7284. Min Act: -0.1700
Data Index: 343020 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7763. Min Range: -2.7763
Max Act: 2.6804. Min Act: -0.1700
Data Index: 1408706 (Python Code)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7763. Min Range: -2.7763
Max Act: 2.6644. Min Act: -0.1700
Data Index: 1626744 (Python Code)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7763. Min Range: -2.7763
Max Act: 2.6644. Min Act: -0.1700
Data Index: 1604852 (Python Code)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7763. Min Range: -2.7763
Max Act: 2.6644. Min Act: -0.1700
Data Index: 1470241 (Python Code)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7763. Min Range: -2.7763
Max Act: 2.6483. Min Act: -0.1700
Data Index: 1511706 (Python Code)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7763. Min Range: -2.7763
Max Act: 2.6483. Min Act: -0.1700
Data Index: 1420992 (Python Code)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7763. Min Range: -2.7763
Max Act: 2.6323. Min Act: -0.1699
Data Index: 1408660 (Python Code)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7763. Min Range: -2.7763
Max Act: 2.6323. Min Act: -0.1700
Data Index: 1392765 (Python Code)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7763. Min Range: -2.7763
Max Act: 2.6323. Min Act: -0.1698
Data Index: 1440623 (Python Code)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7763. Min Range: -2.7763
Max Act: 2.6162. Min Act: -0.1700
Data Index: 1625636 (Python Code)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7763. Min Range: -2.7763
Max Act: 2.6162. Min Act: -0.1700
Data Index: 1460349 (Python Code)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7763. Min Range: -2.7763
Max Act: 2.6162. Min Act: -0.1700
Data Index: 1637208 (Python Code)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7763. Min Range: -2.7763
Max Act: 2.6162. Min Act: -0.1700
Data Index: 75336 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7763. Min Range: -2.7763
Max Act: 2.6162. Min Act: -0.1700
Data Index: 1383637 (Python Code)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7763. Min Range: -2.7763
Max Act: 2.6001. Min Act: -0.1700
Data Index: 1396849 (Python Code)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7763. Min Range: -2.7763
Max Act: 2.6001. Min Act: -0.1700
Data Index: 1600627 (Python Code)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19