Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2005 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.0462. Min Range: -3.0462
Max Act: 3.0462. Min Act: -0.1700
Data Index: 1561905 (Python Code)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0462. Min Range: -3.0462
Max Act: 3.0462. Min Act: -0.1700
Data Index: 1527204 (Python Code)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0462. Min Range: -3.0462
Max Act: 3.0304. Min Act: -0.1700
Data Index: 1531645 (Python Code)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0462. Min Range: -3.0462
Max Act: 3.0146. Min Act: -0.1700
Data Index: 1390386 (Python Code)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0462. Min Range: -3.0462
Max Act: 3.0146. Min Act: -0.1700
Data Index: 1439308 (Python Code)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0462. Min Range: -3.0462
Max Act: 3.0146. Min Act: -0.1700
Data Index: 1627293 (Python Code)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0462. Min Range: -3.0462
Max Act: 2.9988. Min Act: -0.1700
Data Index: 1394588 (Python Code)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0462. Min Range: -3.0462
Max Act: 2.9830. Min Act: -0.1700
Data Index: 1566569 (Python Code)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0462. Min Range: -3.0462
Max Act: 2.9830. Min Act: -0.1700
Data Index: 1516473 (Python Code)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0462. Min Range: -3.0462
Max Act: 2.9830. Min Act: -0.1700
Data Index: 1629918 (Python Code)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0462. Min Range: -3.0462
Max Act: 2.9671. Min Act: -0.1700
Data Index: 1379850 (Python Code)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0462. Min Range: -3.0462
Max Act: 2.9671. Min Act: -0.1700
Data Index: 1586091 (Python Code)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0462. Min Range: -3.0462
Max Act: 2.9513. Min Act: -0.1700
Data Index: 1575841 (Python Code)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0462. Min Range: -3.0462
Max Act: 2.9671. Min Act: -0.1700
Data Index: 1553508 (Python Code)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0462. Min Range: -3.0462
Max Act: 2.9671. Min Act: -0.1700
Data Index: 1359876 (Python Code)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0462. Min Range: -3.0462
Max Act: 2.9830. Min Act: -0.1700
Data Index: 1558660 (Python Code)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0462. Min Range: -3.0462
Max Act: 2.9671. Min Act: -0.1700
Data Index: 1563412 (Python Code)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0462. Min Range: -3.0462
Max Act: 2.9671. Min Act: -0.1700
Data Index: 1411899 (Python Code)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0462. Min Range: -3.0462
Max Act: 2.9513. Min Act: -0.1700
Data Index: 1633082 (Python Code)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0462. Min Range: -3.0462
Max Act: 2.9513. Min Act: -0.1700
Data Index: 1391784 (Python Code)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19