Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1945 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8782. Min Range: -2.8782
Max Act: 2.8782. Min Act: -0.1700
Data Index: 722370 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8782. Min Range: -2.8782
Max Act: 2.6228. Min Act: -0.1700
Data Index: 105162 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8782. Min Range: -2.8782
Max Act: 2.5906. Min Act: -0.1700
Data Index: 125604 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8782. Min Range: -2.8782
Max Act: 2.5906. Min Act: -0.1700
Data Index: 454790 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8782. Min Range: -2.8782
Max Act: 2.5745. Min Act: -0.1700
Data Index: 207587 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8782. Min Range: -2.8782
Max Act: 2.5745. Min Act: -0.1700
Data Index: 1128413 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8782. Min Range: -2.8782
Max Act: 2.5745. Min Act: -0.1700
Data Index: 906091 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8782. Min Range: -2.8782
Max Act: 2.5584. Min Act: -0.1700
Data Index: 1179633 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8782. Min Range: -2.8782
Max Act: 2.5745. Min Act: -0.1700
Data Index: 150115 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8782. Min Range: -2.8782
Max Act: 2.5584. Min Act: -0.1700
Data Index: 242910 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8782. Min Range: -2.8782
Max Act: 2.5422. Min Act: -0.1700
Data Index: 1122558 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8782. Min Range: -2.8782
Max Act: 2.5422. Min Act: -0.1700
Data Index: 290847 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8782. Min Range: -2.8782
Max Act: 2.5099. Min Act: -0.1700
Data Index: 198631 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8782. Min Range: -2.8782
Max Act: 2.5099. Min Act: -0.1700
Data Index: 751785 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8782. Min Range: -2.8782
Max Act: 2.5099. Min Act: -0.1700
Data Index: 450892 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8782. Min Range: -2.8782
Max Act: 2.4937. Min Act: -0.1700
Data Index: 917795 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8782. Min Range: -2.8782
Max Act: 2.4937. Min Act: -0.1700
Data Index: 599385 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8782. Min Range: -2.8782
Max Act: 2.4937. Min Act: -0.1700
Data Index: 902532 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8782. Min Range: -2.8782
Max Act: 2.4937. Min Act: -0.1700
Data Index: 91849 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8782. Min Range: -2.8782
Max Act: 2.4775. Min Act: -0.1700
Data Index: 364033 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19