Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 73 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4005. Min Range: -2.4005
Max Act: 2.4005. Min Act: -0.1700
Data Index: 921743 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4005. Min Range: -2.4005
Max Act: 2.2858. Min Act: -0.1700
Data Index: 667652 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4005. Min Range: -2.4005
Max Act: 2.2693. Min Act: -0.1700
Data Index: 559233 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4005. Min Range: -2.4005
Max Act: 2.2693. Min Act: -0.1700
Data Index: 1312938 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4005. Min Range: -2.4005
Max Act: 2.2693. Min Act: -0.1700
Data Index: 493476 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4005. Min Range: -2.4005
Max Act: 2.2363. Min Act: -0.1700
Data Index: 269436 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4005. Min Range: -2.4005
Max Act: 2.2363. Min Act: -0.1700
Data Index: 1178023 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4005. Min Range: -2.4005
Max Act: 2.2197. Min Act: -0.1700
Data Index: 933168 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4005. Min Range: -2.4005
Max Act: 2.2197. Min Act: -0.1700
Data Index: 1211780 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4005. Min Range: -2.4005
Max Act: 2.2528. Min Act: -0.1700
Data Index: 150591 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4005. Min Range: -2.4005
Max Act: 2.2032. Min Act: -0.1700
Data Index: 39562 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4005. Min Range: -2.4005
Max Act: 2.2197. Min Act: -0.1700
Data Index: 1330353 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4005. Min Range: -2.4005
Max Act: 2.2032. Min Act: -0.1700
Data Index: 1076906 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4005. Min Range: -2.4005
Max Act: 2.2032. Min Act: -0.1700
Data Index: 34263 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4005. Min Range: -2.4005
Max Act: 2.2032. Min Act: -0.1700
Data Index: 1304981 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4005. Min Range: -2.4005
Max Act: 2.2032. Min Act: -0.1700
Data Index: 419739 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4005. Min Range: -2.4005
Max Act: 2.1866. Min Act: -0.1700
Data Index: 796534 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4005. Min Range: -2.4005
Max Act: 2.1866. Min Act: -0.1700
Data Index: 419593 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4005. Min Range: -2.4005
Max Act: 2.2032. Min Act: -0.1700
Data Index: 691918 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4005. Min Range: -2.4005
Max Act: 2.1866. Min Act: -0.1700
Data Index: 178343 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19