Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1982 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5693. Min Range: -2.5693
Max Act: 2.5532. Min Act: -0.1700
Data Index: 831387 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5693. Min Range: -2.5693
Max Act: 2.5693. Min Act: -0.1700
Data Index: 1186454 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5693. Min Range: -2.5693
Max Act: 2.5370. Min Act: -0.1700
Data Index: 988472 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5693. Min Range: -2.5693
Max Act: 2.5047. Min Act: -0.1700
Data Index: 1301995 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5693. Min Range: -2.5693
Max Act: 2.5047. Min Act: -0.1700
Data Index: 1096389 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5693. Min Range: -2.5693
Max Act: 2.5047. Min Act: -0.1700
Data Index: 470979 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5693. Min Range: -2.5693
Max Act: 2.4885. Min Act: -0.1700
Data Index: 252883 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5693. Min Range: -2.5693
Max Act: 2.4723. Min Act: -0.1700
Data Index: 942197 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5693. Min Range: -2.5693
Max Act: 2.4723. Min Act: -0.1700
Data Index: 1122769 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5693. Min Range: -2.5693
Max Act: 2.4560. Min Act: -0.1700
Data Index: 992402 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5693. Min Range: -2.5693
Max Act: 2.4398. Min Act: -0.1700
Data Index: 1237511 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5693. Min Range: -2.5693
Max Act: 2.4560. Min Act: -0.1700
Data Index: 695136 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5693. Min Range: -2.5693
Max Act: 2.4560. Min Act: -0.1700
Data Index: 460532 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5693. Min Range: -2.5693
Max Act: 2.4235. Min Act: -0.1700
Data Index: 462777 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5693. Min Range: -2.5693
Max Act: 2.4560. Min Act: -0.1700
Data Index: 1176094 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5693. Min Range: -2.5693
Max Act: 2.4560. Min Act: -0.1700
Data Index: 842543 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5693. Min Range: -2.5693
Max Act: 2.4398. Min Act: -0.1700
Data Index: 764068 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5693. Min Range: -2.5693
Max Act: 2.4398. Min Act: -0.1700
Data Index: 885762 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5693. Min Range: -2.5693
Max Act: 2.4560. Min Act: -0.1700
Data Index: 1219305 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5693. Min Range: -2.5693
Max Act: 2.4398. Min Act: -0.1700
Data Index: 202565 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19