Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2032 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8111. Min Range: -2.8111
Max Act: 2.8111. Min Act: -0.1700
Data Index: 292029 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8111. Min Range: -2.8111
Max Act: 2.7952. Min Act: -0.1700
Data Index: 438300 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8111. Min Range: -2.8111
Max Act: 2.7792. Min Act: -0.1700
Data Index: 812791 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8111. Min Range: -2.8111
Max Act: 2.7792. Min Act: -0.1700
Data Index: 485293 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8111. Min Range: -2.8111
Max Act: 2.7633. Min Act: -0.1700
Data Index: 941681 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8111. Min Range: -2.8111
Max Act: 2.7792. Min Act: -0.1700
Data Index: 242065 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8111. Min Range: -2.8111
Max Act: 2.7633. Min Act: -0.1700
Data Index: 414463 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8111. Min Range: -2.8111
Max Act: 2.7473. Min Act: -0.1700
Data Index: 569896 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8111. Min Range: -2.8111
Max Act: 2.7473. Min Act: -0.1700
Data Index: 1253851 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8111. Min Range: -2.8111
Max Act: 2.7313. Min Act: -0.1700
Data Index: 558027 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8111. Min Range: -2.8111
Max Act: 2.7473. Min Act: -0.1700
Data Index: 764607 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8111. Min Range: -2.8111
Max Act: 2.7633. Min Act: -0.1700
Data Index: 1113330 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8111. Min Range: -2.8111
Max Act: 2.7313. Min Act: -0.1700
Data Index: 554556 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8111. Min Range: -2.8111
Max Act: 2.7313. Min Act: -0.1700
Data Index: 606001 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8111. Min Range: -2.8111
Max Act: 2.7313. Min Act: -0.1700
Data Index: 1049977 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8111. Min Range: -2.8111
Max Act: 2.7313. Min Act: -0.1700
Data Index: 1626 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8111. Min Range: -2.8111
Max Act: 2.7313. Min Act: -0.1700
Data Index: 327470 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8111. Min Range: -2.8111
Max Act: 2.7313. Min Act: -0.1700
Data Index: 553591 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8111. Min Range: -2.8111
Max Act: 2.7154. Min Act: -0.1700
Data Index: 909539 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8111. Min Range: -2.8111
Max Act: 2.7313. Min Act: -0.1700
Data Index: 699726 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19