Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1962 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.3328. Min Range: -3.3328
Max Act: 3.3328. Min Act: -0.1700
Data Index: 1612485 (Python Code)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3328. Min Range: -3.3328
Max Act: 3.3328. Min Act: -0.1700
Data Index: 1149409 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3328. Min Range: -3.3328
Max Act: 3.3171. Min Act: -0.1700
Data Index: 949703 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3328. Min Range: -3.3328
Max Act: 3.3014. Min Act: -0.1700
Data Index: 161481 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3328. Min Range: -3.3328
Max Act: 3.3014. Min Act: -0.1700
Data Index: 1465842 (Python Code)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3328. Min Range: -3.3328
Max Act: 3.2857. Min Act: -0.1700
Data Index: 1577633 (Python Code)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3328. Min Range: -3.3328
Max Act: 3.3014. Min Act: -0.1700
Data Index: 830841 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3328. Min Range: -3.3328
Max Act: 3.2700. Min Act: -0.1700
Data Index: 1640118 (Python Code)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3328. Min Range: -3.3328
Max Act: 3.2700. Min Act: -0.1700
Data Index: 1474559 (Python Code)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3328. Min Range: -3.3328
Max Act: 3.2857. Min Act: -0.1700
Data Index: 79079 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3328. Min Range: -3.3328
Max Act: 3.2386. Min Act: -0.1700
Data Index: 1449711 (Python Code)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3328. Min Range: -3.3328
Max Act: 3.2543. Min Act: -0.1700
Data Index: 1191181 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3328. Min Range: -3.3328
Max Act: 3.2386. Min Act: -0.1700
Data Index: 1327191 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3328. Min Range: -3.3328
Max Act: 3.2543. Min Act: -0.1700
Data Index: 1449770 (Python Code)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3328. Min Range: -3.3328
Max Act: 3.2386. Min Act: -0.1700
Data Index: 1604790 (Python Code)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3328. Min Range: -3.3328
Max Act: 3.2386. Min Act: -0.1700
Data Index: 1432184 (Python Code)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3328. Min Range: -3.3328
Max Act: 3.2071. Min Act: -0.1700
Data Index: 1555470 (Python Code)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3328. Min Range: -3.3328
Max Act: 3.2071. Min Act: -0.1700
Data Index: 1649482 (Python Code)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3328. Min Range: -3.3328
Max Act: 3.2228. Min Act: -0.1700
Data Index: 1586345 (Python Code)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3328. Min Range: -3.3328
Max Act: 3.2071. Min Act: -0.1700
Data Index: 1492582 (Python Code)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19