Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1293 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.4783. Min Range: -2.4783
Max Act: 2.4783. Min Act: -0.1700
Data Index: 349648 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4783. Min Range: -2.4783
Max Act: 2.4132. Min Act: -0.1700
Data Index: 1031686 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4783. Min Range: -2.4783
Max Act: 2.4458. Min Act: -0.1700
Data Index: 1285208 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4783. Min Range: -2.4783
Max Act: 2.3643. Min Act: -0.1700
Data Index: 1068183 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4783. Min Range: -2.4783
Max Act: 2.3479. Min Act: -0.1700
Data Index: 399098 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4783. Min Range: -2.4783
Max Act: 2.3479. Min Act: -0.1700
Data Index: 52578 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4783. Min Range: -2.4783
Max Act: 2.3479. Min Act: -0.1700
Data Index: 41380 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4783. Min Range: -2.4783
Max Act: 2.3643. Min Act: -0.1700
Data Index: 577358 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4783. Min Range: -2.4783
Max Act: 2.3315. Min Act: -0.1700
Data Index: 389222 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4783. Min Range: -2.4783
Max Act: 2.3479. Min Act: -0.1700
Data Index: 1012069 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4783. Min Range: -2.4783
Max Act: 2.3151. Min Act: -0.1700
Data Index: 581076 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4783. Min Range: -2.4783
Max Act: 2.3151. Min Act: -0.1700
Data Index: 570654 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4783. Min Range: -2.4783
Max Act: 2.3151. Min Act: -0.1700
Data Index: 162669 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4783. Min Range: -2.4783
Max Act: 2.3151. Min Act: -0.1700
Data Index: 179936 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4783. Min Range: -2.4783
Max Act: 2.2987. Min Act: -0.1700
Data Index: 1022048 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4783. Min Range: -2.4783
Max Act: 2.3151. Min Act: -0.1700
Data Index: 677638 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4783. Min Range: -2.4783
Max Act: 2.2987. Min Act: -0.1700
Data Index: 319623 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4783. Min Range: -2.4783
Max Act: 2.2822. Min Act: -0.1700
Data Index: 149171 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4783. Min Range: -2.4783
Max Act: 2.2987. Min Act: -0.1700
Data Index: 835730 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4783. Min Range: -2.4783
Max Act: 2.2987. Min Act: -0.1700
Data Index: 653717 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19