Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2038 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.5145. Min Range: -4.5145
Max Act: 4.5145. Min Act: -0.1700
Data Index: 923163 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5145. Min Range: -4.5145
Max Act: 4.2020. Min Act: -0.1700
Data Index: 619662 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5145. Min Range: -4.5145
Max Act: 4.1707. Min Act: -0.1700
Data Index: 524353 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5145. Min Range: -4.5145
Max Act: 4.1395. Min Act: -0.1700
Data Index: 1305937 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5145. Min Range: -4.5145
Max Act: 4.0457. Min Act: -0.1700
Data Index: 1008819 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5145. Min Range: -4.5145
Max Act: 4.0457. Min Act: -0.1700
Data Index: 484693 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5145. Min Range: -4.5145
Max Act: 4.0144. Min Act: -0.1700
Data Index: 605155 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5145. Min Range: -4.5145
Max Act: 4.0144. Min Act: -0.1700
Data Index: 91098 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5145. Min Range: -4.5145
Max Act: 3.9831. Min Act: -0.1700
Data Index: 563311 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5145. Min Range: -4.5145
Max Act: 3.9831. Min Act: -0.1700
Data Index: 1029660 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5145. Min Range: -4.5145
Max Act: 3.9206. Min Act: -0.1700
Data Index: 799601 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5145. Min Range: -4.5145
Max Act: 3.9206. Min Act: -0.1700
Data Index: 217851 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5145. Min Range: -4.5145
Max Act: 3.9206. Min Act: -0.1700
Data Index: 799654 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5145. Min Range: -4.5145
Max Act: 3.9206. Min Act: -0.1698
Data Index: 747009 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5145. Min Range: -4.5145
Max Act: 3.9206. Min Act: -0.1700
Data Index: 1305261 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5145. Min Range: -4.5145
Max Act: 3.8893. Min Act: -0.1700
Data Index: 80101 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5145. Min Range: -4.5145
Max Act: 3.9206. Min Act: -0.1700
Data Index: 623080 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5145. Min Range: -4.5145
Max Act: 3.9206. Min Act: -0.1700
Data Index: 604710 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5145. Min Range: -4.5145
Max Act: 3.8893. Min Act: -0.1700
Data Index: 814214 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5145. Min Range: -4.5145
Max Act: 3.8893. Min Act: -0.1700
Data Index: 396423 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19