Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2046 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0215. Min Range: -3.0215
Max Act: 3.0215. Min Act: -0.1700
Data Index: 1286877 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0215. Min Range: -3.0215
Max Act: 2.9741. Min Act: -0.1700
Data Index: 134443 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0215. Min Range: -3.0215
Max Act: 2.9583. Min Act: -0.1700
Data Index: 565254 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0215. Min Range: -3.0215
Max Act: 2.9107. Min Act: -0.1700
Data Index: 1014637 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0215. Min Range: -3.0215
Max Act: 2.8949. Min Act: -0.1700
Data Index: 360856 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0215. Min Range: -3.0215
Max Act: 2.9107. Min Act: -0.1700
Data Index: 272516 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0215. Min Range: -3.0215
Max Act: 2.8949. Min Act: -0.1700
Data Index: 1605947 (Python Code)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0215. Min Range: -3.0215
Max Act: 2.8949. Min Act: -0.1700
Data Index: 1112915 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0215. Min Range: -3.0215
Max Act: 2.8949. Min Act: -0.1700
Data Index: 364747 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0215. Min Range: -3.0215
Max Act: 2.8949. Min Act: -0.1700
Data Index: 1240981 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0215. Min Range: -3.0215
Max Act: 2.8790. Min Act: -0.1700
Data Index: 1157205 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0215. Min Range: -3.0215
Max Act: 2.8790. Min Act: -0.1700
Data Index: 976992 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0215. Min Range: -3.0215
Max Act: 2.8949. Min Act: -0.1700
Data Index: 456286 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0215. Min Range: -3.0215
Max Act: 2.8790. Min Act: -0.1700
Data Index: 1441528 (Python Code)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0215. Min Range: -3.0215
Max Act: 2.8790. Min Act: -0.1700
Data Index: 1649153 (Python Code)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0215. Min Range: -3.0215
Max Act: 2.8472. Min Act: -0.1700
Data Index: 1421079 (Python Code)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0215. Min Range: -3.0215
Max Act: 2.8472. Min Act: -0.1700
Data Index: 1456250 (Python Code)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0215. Min Range: -3.0215
Max Act: 2.8631. Min Act: -0.1700
Data Index: 1367682 (Python Code)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0215. Min Range: -3.0215
Max Act: 2.8631. Min Act: -0.1700
Data Index: 1287351 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0215. Min Range: -3.0215
Max Act: 2.8472. Min Act: -0.1700
Data Index: 754497 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19