Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2022 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8818. Min Range: -2.8818
Max Act: 2.8818. Min Act: -0.1700
Data Index: 383508 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8818. Min Range: -2.8818
Max Act: 2.8023. Min Act: -0.1700
Data Index: 934748 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8818. Min Range: -2.8818
Max Act: 2.8023. Min Act: -0.1700
Data Index: 1349418 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8818. Min Range: -2.8818
Max Act: 2.7705. Min Act: -0.1700
Data Index: 496987 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8818. Min Range: -2.8818
Max Act: 2.7545. Min Act: -0.1700
Data Index: 849579 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8818. Min Range: -2.8818
Max Act: 2.6745. Min Act: -0.1700
Data Index: 1382066 (Python Code)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8818. Min Range: -2.8818
Max Act: 2.6745. Min Act: -0.1700
Data Index: 704332 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8818. Min Range: -2.8818
Max Act: 2.6745. Min Act: -0.1700
Data Index: 465035 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8818. Min Range: -2.8818
Max Act: 2.6425. Min Act: -0.1700
Data Index: 514453 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8818. Min Range: -2.8818
Max Act: 2.6745. Min Act: -0.1700
Data Index: 1374089 (Python Code)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8818. Min Range: -2.8818
Max Act: 2.6425. Min Act: -0.1700
Data Index: 1556382 (Python Code)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8818. Min Range: -2.8818
Max Act: 2.6425. Min Act: -0.1700
Data Index: 1414812 (Python Code)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8818. Min Range: -2.8818
Max Act: 2.6425. Min Act: -0.1700
Data Index: 1380282 (Python Code)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8818. Min Range: -2.8818
Max Act: 2.6264. Min Act: -0.1700
Data Index: 1582961 (Python Code)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8818. Min Range: -2.8818
Max Act: 2.6425. Min Act: -0.1700
Data Index: 1537836 (Python Code)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8818. Min Range: -2.8818
Max Act: 2.6103. Min Act: -0.1700
Data Index: 1392220 (Python Code)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8818. Min Range: -2.8818
Max Act: 2.6264. Min Act: -0.1700
Data Index: 1519411 (Python Code)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8818. Min Range: -2.8818
Max Act: 2.6264. Min Act: -0.1700
Data Index: 480483 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8818. Min Range: -2.8818
Max Act: 2.6264. Min Act: -0.1700
Data Index: 467478 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8818. Min Range: -2.8818
Max Act: 2.6103. Min Act: -0.1700
Data Index: 1571135 (Python Code)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19