Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1994 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.4024. Min Range: -4.4024
Max Act: 4.3399. Min Act: -0.1700
Data Index: 1410071 (Python Code)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4024. Min Range: -4.4024
Max Act: 4.3399. Min Act: -0.1700
Data Index: 1387058 (Python Code)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4024. Min Range: -4.4024
Max Act: 4.3399. Min Act: -0.1700
Data Index: 1450231 (Python Code)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4024. Min Range: -4.4024
Max Act: 4.4024. Min Act: -0.1700
Data Index: 1390020 (Python Code)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4024. Min Range: -4.4024
Max Act: 4.3712. Min Act: -0.1700
Data Index: 1513791 (Python Code)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4024. Min Range: -4.4024
Max Act: 4.3712. Min Act: -0.1700
Data Index: 1373495 (Python Code)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4024. Min Range: -4.4024
Max Act: 4.3399. Min Act: -0.1700
Data Index: 1436665 (Python Code)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4024. Min Range: -4.4024
Max Act: 4.3712. Min Act: -0.1700
Data Index: 1630888 (Python Code)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4024. Min Range: -4.4024
Max Act: 4.3399. Min Act: -0.1700
Data Index: 1634877 (Python Code)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4024. Min Range: -4.4024
Max Act: 4.3087. Min Act: -0.1700
Data Index: 1589101 (Python Code)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4024. Min Range: -4.4024
Max Act: 4.3087. Min Act: -0.1700
Data Index: 1606500 (Python Code)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4024. Min Range: -4.4024
Max Act: 4.2774. Min Act: -0.1700
Data Index: 1512292 (Python Code)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4024. Min Range: -4.4024
Max Act: 4.3087. Min Act: -0.1700
Data Index: 1624691 (Python Code)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4024. Min Range: -4.4024
Max Act: 4.2149. Min Act: -0.1700
Data Index: 1411756 (Python Code)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4024. Min Range: -4.4024
Max Act: 4.2774. Min Act: -0.1700
Data Index: 1545321 (Python Code)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4024. Min Range: -4.4024
Max Act: 4.3087. Min Act: -0.1700
Data Index: 1542244 (Python Code)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4024. Min Range: -4.4024
Max Act: 4.2462. Min Act: -0.1700
Data Index: 1569559 (Python Code)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4024. Min Range: -4.4024
Max Act: 4.2149. Min Act: -0.1700
Data Index: 1544520 (Python Code)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4024. Min Range: -4.4024
Max Act: 4.2462. Min Act: -0.1700
Data Index: 1590006 (Python Code)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4024. Min Range: -4.4024
Max Act: 4.2774. Min Act: -0.1700
Data Index: 1381956 (Python Code)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19