Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 996 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.6204. Min Range: -2.6204
Max Act: 2.6043. Min Act: -0.1700
Data Index: 85797 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6204. Min Range: -2.6204
Max Act: 2.5882. Min Act: -0.1700
Data Index: 1079168 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6204. Min Range: -2.6204
Max Act: 2.6204. Min Act: -0.1700
Data Index: 970017 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6204. Min Range: -2.6204
Max Act: 2.6043. Min Act: -0.1700
Data Index: 34868 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6204. Min Range: -2.6204
Max Act: 2.5398. Min Act: -0.1700
Data Index: 1345718 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6204. Min Range: -2.6204
Max Act: 2.5559. Min Act: -0.1700
Data Index: 1175510 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6204. Min Range: -2.6204
Max Act: 2.5398. Min Act: -0.1700
Data Index: 1090208 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6204. Min Range: -2.6204
Max Act: 2.5236. Min Act: -0.1700
Data Index: 645314 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6204. Min Range: -2.6204
Max Act: 2.5075. Min Act: -0.1700
Data Index: 61095 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6204. Min Range: -2.6204
Max Act: 2.5236. Min Act: -0.1700
Data Index: 1112700 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6204. Min Range: -2.6204
Max Act: 2.4913. Min Act: -0.1700
Data Index: 113310 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6204. Min Range: -2.6204
Max Act: 2.4913. Min Act: -0.1700
Data Index: 277922 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6204. Min Range: -2.6204
Max Act: 2.4750. Min Act: -0.1700
Data Index: 1211514 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6204. Min Range: -2.6204
Max Act: 2.4426. Min Act: -0.1700
Data Index: 957065 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6204. Min Range: -2.6204
Max Act: 2.4426. Min Act: -0.1700
Data Index: 187052 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6204. Min Range: -2.6204
Max Act: 2.4588. Min Act: -0.1700
Data Index: 645955 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6204. Min Range: -2.6204
Max Act: 2.4426. Min Act: -0.1700
Data Index: 372742 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6204. Min Range: -2.6204
Max Act: 2.4426. Min Act: -0.1700
Data Index: 507026 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6204. Min Range: -2.6204
Max Act: 2.4426. Min Act: -0.1700
Data Index: 69541 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6204. Min Range: -2.6204
Max Act: 2.4426. Min Act: -0.1700
Data Index: 135006 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19