Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 217 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7634. Min Range: -4.7634
Max Act: 4.7634. Min Act: -0.1700
Data Index: 846492 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7634. Min Range: -4.7634
Max Act: 4.5134. Min Act: -0.1700
Data Index: 1006552 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7634. Min Range: -4.7634
Max Act: 4.5447. Min Act: -0.1700
Data Index: 753081 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7634. Min Range: -4.7634
Max Act: 4.5447. Min Act: -0.1700
Data Index: 792202 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7634. Min Range: -4.7634
Max Act: 4.3884. Min Act: -0.1700
Data Index: 502358 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7634. Min Range: -4.7634
Max Act: 4.4822. Min Act: -0.1700
Data Index: 987798 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7634. Min Range: -4.7634
Max Act: 4.4509. Min Act: -0.1700
Data Index: 397371 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7634. Min Range: -4.7634
Max Act: 4.3572. Min Act: -0.1700
Data Index: 838041 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7634. Min Range: -4.7634
Max Act: 4.3259. Min Act: -0.1700
Data Index: 645446 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7634. Min Range: -4.7634
Max Act: 4.3572. Min Act: -0.1700
Data Index: 383479 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7634. Min Range: -4.7634
Max Act: 4.3572. Min Act: -0.1700
Data Index: 903559 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7634. Min Range: -4.7634
Max Act: 4.3259. Min Act: -0.1700
Data Index: 588580 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7634. Min Range: -4.7634
Max Act: 4.3572. Min Act: -0.1700
Data Index: 484421 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7634. Min Range: -4.7634
Max Act: 4.3884. Min Act: -0.1700
Data Index: 670253 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7634. Min Range: -4.7634
Max Act: 4.2634. Min Act: -0.1700
Data Index: 1145653 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7634. Min Range: -4.7634
Max Act: 4.3884. Min Act: -0.1700
Data Index: 1133835 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7634. Min Range: -4.7634
Max Act: 4.3572. Min Act: -0.1700
Data Index: 866321 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7634. Min Range: -4.7634
Max Act: 4.2946. Min Act: -0.1700
Data Index: 1100568 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7634. Min Range: -4.7634
Max Act: 4.2946. Min Act: -0.1700
Data Index: 699596 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7634. Min Range: -4.7634
Max Act: 4.3259. Min Act: -0.1700
Data Index: 33449 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19