Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1955 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8740. Min Range: -2.8740
Max Act: 2.8740. Min Act: -0.1700
Data Index: 480824 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8740. Min Range: -2.8740
Max Act: 2.8263. Min Act: -0.1700
Data Index: 188389 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8740. Min Range: -2.8740
Max Act: 2.7785. Min Act: -0.1700
Data Index: 582151 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8740. Min Range: -2.8740
Max Act: 2.7466. Min Act: -0.1700
Data Index: 605040 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8740. Min Range: -2.8740
Max Act: 2.7626. Min Act: -0.1700
Data Index: 1207090 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8740. Min Range: -2.8740
Max Act: 2.7307. Min Act: -0.1700
Data Index: 727209 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8740. Min Range: -2.8740
Max Act: 2.7307. Min Act: -0.1700
Data Index: 54371 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8740. Min Range: -2.8740
Max Act: 2.7307. Min Act: -0.1700
Data Index: 461868 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8740. Min Range: -2.8740
Max Act: 2.7307. Min Act: -0.1700
Data Index: 573167 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8740. Min Range: -2.8740
Max Act: 2.7307. Min Act: -0.1700
Data Index: 353930 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8740. Min Range: -2.8740
Max Act: 2.7307. Min Act: -0.1700
Data Index: 347887 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8740. Min Range: -2.8740
Max Act: 2.7147. Min Act: -0.1700
Data Index: 474790 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8740. Min Range: -2.8740
Max Act: 2.6987. Min Act: -0.1700
Data Index: 703014 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8740. Min Range: -2.8740
Max Act: 2.7147. Min Act: -0.1700
Data Index: 295652 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8740. Min Range: -2.8740
Max Act: 2.6666. Min Act: -0.1700
Data Index: 822325 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8740. Min Range: -2.8740
Max Act: 2.6987. Min Act: -0.1700
Data Index: 395036 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8740. Min Range: -2.8740
Max Act: 2.6827. Min Act: -0.1700
Data Index: 502095 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8740. Min Range: -2.8740
Max Act: 2.6827. Min Act: -0.1700
Data Index: 1322297 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8740. Min Range: -2.8740
Max Act: 2.6666. Min Act: -0.1700
Data Index: 848433 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8740. Min Range: -2.8740
Max Act: 2.6506. Min Act: -0.1700
Data Index: 912160 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19