Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1532 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0855. Min Range: -3.0855
Max Act: 3.0855. Min Act: -0.1700
Data Index: 249529 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0855. Min Range: -3.0855
Max Act: 3.0539. Min Act: -0.1700
Data Index: 699895 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0855. Min Range: -3.0855
Max Act: 2.9908. Min Act: -0.1700
Data Index: 589898 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0855. Min Range: -3.0855
Max Act: 2.9274. Min Act: -0.1700
Data Index: 473779 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0855. Min Range: -3.0855
Max Act: 2.9116. Min Act: -0.1700
Data Index: 565861 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0855. Min Range: -3.0855
Max Act: 2.8957. Min Act: -0.1700
Data Index: 763441 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0855. Min Range: -3.0855
Max Act: 2.8957. Min Act: -0.1700
Data Index: 422239 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0855. Min Range: -3.0855
Max Act: 2.8640. Min Act: -0.1700
Data Index: 69738 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0855. Min Range: -3.0855
Max Act: 2.8640. Min Act: -0.1700
Data Index: 732518 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0855. Min Range: -3.0855
Max Act: 2.9116. Min Act: -0.1700
Data Index: 669150 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0855. Min Range: -3.0855
Max Act: 2.8798. Min Act: -0.1700
Data Index: 168323 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0855. Min Range: -3.0855
Max Act: 2.8640. Min Act: -0.1700
Data Index: 805696 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0855. Min Range: -3.0855
Max Act: 2.8481. Min Act: -0.1700
Data Index: 698767 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0855. Min Range: -3.0855
Max Act: 2.8481. Min Act: -0.1700
Data Index: 684851 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0855. Min Range: -3.0855
Max Act: 2.8481. Min Act: -0.1700
Data Index: 117031 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0855. Min Range: -3.0855
Max Act: 2.8322. Min Act: -0.1700
Data Index: 1298745 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0855. Min Range: -3.0855
Max Act: 2.8322. Min Act: -0.1700
Data Index: 460383 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0855. Min Range: -3.0855
Max Act: 2.8322. Min Act: -0.1700
Data Index: 650573 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0855. Min Range: -3.0855
Max Act: 2.8163. Min Act: -0.1700
Data Index: 1144801 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0855. Min Range: -3.0855
Max Act: 2.8163. Min Act: -0.1700
Data Index: 100537 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19