Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 726 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.4211. Min Range: -4.4211
Max Act: 4.4211. Min Act: -0.1700
Data Index: 707218 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4211. Min Range: -4.4211
Max Act: 4.4211. Min Act: -0.1700
Data Index: 431868 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4211. Min Range: -4.4211
Max Act: 4.3899. Min Act: -0.1700
Data Index: 913385 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4211. Min Range: -4.4211
Max Act: 4.3274. Min Act: -0.1700
Data Index: 879224 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4211. Min Range: -4.4211
Max Act: 4.2649. Min Act: -0.1700
Data Index: 944393 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4211. Min Range: -4.4211
Max Act: 4.2961. Min Act: -0.1700
Data Index: 1052221 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4211. Min Range: -4.4211
Max Act: 4.2336. Min Act: -0.1700
Data Index: 837644 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4211. Min Range: -4.4211
Max Act: 4.2024. Min Act: -0.1700
Data Index: 1134760 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4211. Min Range: -4.4211
Max Act: 4.2336. Min Act: -0.1700
Data Index: 518052 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4211. Min Range: -4.4211
Max Act: 4.1711. Min Act: -0.1700
Data Index: 1337105 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4211. Min Range: -4.4211
Max Act: 4.1398. Min Act: -0.1700
Data Index: 909671 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4211. Min Range: -4.4211
Max Act: 4.1086. Min Act: -0.1700
Data Index: 368940 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4211. Min Range: -4.4211
Max Act: 4.1711. Min Act: -0.1700
Data Index: 694012 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4211. Min Range: -4.4211
Max Act: 4.1398. Min Act: -0.1700
Data Index: 1196772 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4211. Min Range: -4.4211
Max Act: 4.1086. Min Act: -0.1700
Data Index: 1218736 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4211. Min Range: -4.4211
Max Act: 4.0773. Min Act: -0.1700
Data Index: 77377 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4211. Min Range: -4.4211
Max Act: 4.1086. Min Act: -0.1700
Data Index: 165131 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4211. Min Range: -4.4211
Max Act: 4.0773. Min Act: -0.1700
Data Index: 86023 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4211. Min Range: -4.4211
Max Act: 4.0773. Min Act: -0.1700
Data Index: 1031759 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4211. Min Range: -4.4211
Max Act: 4.0773. Min Act: -0.1700
Data Index: 814884 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19