Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1026 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9017. Min Range: -2.9017
Max Act: 2.9017. Min Act: -0.1700
Data Index: 487706 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9017. Min Range: -2.9017
Max Act: 2.8700. Min Act: -0.1700
Data Index: 722579 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9017. Min Range: -2.9017
Max Act: 2.8700. Min Act: -0.1700
Data Index: 151940 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9017. Min Range: -2.9017
Max Act: 2.8700. Min Act: -0.1700
Data Index: 519912 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9017. Min Range: -2.9017
Max Act: 2.8541. Min Act: -0.1700
Data Index: 1269469 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9017. Min Range: -2.9017
Max Act: 2.8223. Min Act: -0.1700
Data Index: 125461 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9017. Min Range: -2.9017
Max Act: 2.8382. Min Act: -0.1700
Data Index: 1107295 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9017. Min Range: -2.9017
Max Act: 2.7904. Min Act: -0.1700
Data Index: 273623 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9017. Min Range: -2.9017
Max Act: 2.7745. Min Act: -0.1700
Data Index: 1247191 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9017. Min Range: -2.9017
Max Act: 2.7745. Min Act: -0.1700
Data Index: 130247 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9017. Min Range: -2.9017
Max Act: 2.7745. Min Act: -0.1700
Data Index: 148507 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9017. Min Range: -2.9017
Max Act: 2.7586. Min Act: -0.1700
Data Index: 853340 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9017. Min Range: -2.9017
Max Act: 2.7586. Min Act: -0.1700
Data Index: 1289822 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9017. Min Range: -2.9017
Max Act: 2.7745. Min Act: -0.1700
Data Index: 1001832 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9017. Min Range: -2.9017
Max Act: 2.7904. Min Act: -0.1700
Data Index: 1203211 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9017. Min Range: -2.9017
Max Act: 2.7426. Min Act: -0.1700
Data Index: 937340 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9017. Min Range: -2.9017
Max Act: 2.7586. Min Act: -0.1700
Data Index: 1044731 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9017. Min Range: -2.9017
Max Act: 2.7586. Min Act: -0.1700
Data Index: 582448 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9017. Min Range: -2.9017
Max Act: 2.7586. Min Act: -0.1700
Data Index: 66034 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9017. Min Range: -2.9017
Max Act: 2.7266. Min Act: -0.1700
Data Index: 1202628 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19