Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1477 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 5.0661. Min Range: -5.0661
Max Act: 5.0661. Min Act: -0.1700
Data Index: 931865 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0661. Min Range: -5.0661
Max Act: 4.9723. Min Act: -0.1700
Data Index: 426847 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0661. Min Range: -5.0661
Max Act: 4.8786. Min Act: -0.1700
Data Index: 782409 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0661. Min Range: -5.0661
Max Act: 4.8473. Min Act: -0.1700
Data Index: 35140 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0661. Min Range: -5.0661
Max Act: 4.9098. Min Act: -0.1700
Data Index: 1333790 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0661. Min Range: -5.0661
Max Act: 4.8473. Min Act: -0.1700
Data Index: 244665 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0661. Min Range: -5.0661
Max Act: 4.8161. Min Act: -0.1700
Data Index: 222154 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0661. Min Range: -5.0661
Max Act: 4.8161. Min Act: -0.1700
Data Index: 1020341 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0661. Min Range: -5.0661
Max Act: 4.8161. Min Act: -0.1700
Data Index: 583723 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0661. Min Range: -5.0661
Max Act: 4.8473. Min Act: -0.1700
Data Index: 1228402 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0661. Min Range: -5.0661
Max Act: 4.7536. Min Act: -0.1700
Data Index: 186015 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0661. Min Range: -5.0661
Max Act: 4.8161. Min Act: -0.1700
Data Index: 172284 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0661. Min Range: -5.0661
Max Act: 4.7536. Min Act: -0.1700
Data Index: 693960 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0661. Min Range: -5.0661
Max Act: 4.7536. Min Act: -0.1700
Data Index: 1311632 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0661. Min Range: -5.0661
Max Act: 4.7848. Min Act: -0.1700
Data Index: 201747 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0661. Min Range: -5.0661
Max Act: 4.7536. Min Act: -0.1700
Data Index: 1128627 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0661. Min Range: -5.0661
Max Act: 4.7848. Min Act: -0.1700
Data Index: 871281 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0661. Min Range: -5.0661
Max Act: 4.7536. Min Act: -0.1700
Data Index: 860647 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0661. Min Range: -5.0661
Max Act: 4.7536. Min Act: -0.1700
Data Index: 945581 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0661. Min Range: -5.0661
Max Act: 4.7223. Min Act: -0.1700
Data Index: 418102 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19