Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2004 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3401. Min Range: -4.3401
Max Act: 4.3401. Min Act: -0.1700
Data Index: 863911 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3401. Min Range: -4.3401
Max Act: 4.2150. Min Act: -0.1700
Data Index: 57761 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3401. Min Range: -4.3401
Max Act: 4.2150. Min Act: -0.1700
Data Index: 157047 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3401. Min Range: -4.3401
Max Act: 4.1525. Min Act: -0.1700
Data Index: 1204669 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3401. Min Range: -4.3401
Max Act: 4.1525. Min Act: -0.1700
Data Index: 1199485 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3401. Min Range: -4.3401
Max Act: 4.0900. Min Act: -0.1700
Data Index: 1232812 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3401. Min Range: -4.3401
Max Act: 4.0900. Min Act: -0.1700
Data Index: 574523 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3401. Min Range: -4.3401
Max Act: 4.0900. Min Act: -0.1700
Data Index: 1132135 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3401. Min Range: -4.3401
Max Act: 4.0900. Min Act: -0.1700
Data Index: 1126370 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3401. Min Range: -4.3401
Max Act: 4.0900. Min Act: -0.1700
Data Index: 928641 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3401. Min Range: -4.3401
Max Act: 4.0900. Min Act: -0.1700
Data Index: 769489 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3401. Min Range: -4.3401
Max Act: 4.0587. Min Act: -0.1700
Data Index: 953440 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3401. Min Range: -4.3401
Max Act: 4.0587. Min Act: -0.1700
Data Index: 75912 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3401. Min Range: -4.3401
Max Act: 4.0900. Min Act: -0.1700
Data Index: 235199 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3401. Min Range: -4.3401
Max Act: 4.0275. Min Act: -0.1700
Data Index: 305217 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3401. Min Range: -4.3401
Max Act: 4.0587. Min Act: -0.1700
Data Index: 248967 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3401. Min Range: -4.3401
Max Act: 4.0275. Min Act: -0.1700
Data Index: 535947 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3401. Min Range: -4.3401
Max Act: 4.0587. Min Act: -0.1700
Data Index: 1066885 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3401. Min Range: -4.3401
Max Act: 4.0275. Min Act: -0.1700
Data Index: 508681 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3401. Min Range: -4.3401
Max Act: 4.0587. Min Act: -0.1700
Data Index: 240965 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19