Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 13 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.7043. Min Range: -6.7043
Max Act: 6.7043. Min Act: -0.1699
Data Index: 1066333 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7043. Min Range: -6.7043
Max Act: 6.4387. Min Act: -0.1699
Data Index: 704373 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7043. Min Range: -6.7043
Max Act: 6.3762. Min Act: -0.1699
Data Index: 656980 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7043. Min Range: -6.7043
Max Act: 6.3137. Min Act: -0.1699
Data Index: 497023 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7043. Min Range: -6.7043
Max Act: 6.2668. Min Act: -0.1699
Data Index: 700542 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7043. Min Range: -6.7043
Max Act: 6.1575. Min Act: -0.1699
Data Index: 75608 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7043. Min Range: -6.7043
Max Act: 6.2512. Min Act: -0.1699
Data Index: 788051 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7043. Min Range: -6.7043
Max Act: 6.1731. Min Act: -0.1699
Data Index: 412856 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7043. Min Range: -6.7043
Max Act: 6.2043. Min Act: -0.1699
Data Index: 1111437 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7043. Min Range: -6.7043
Max Act: 6.2043. Min Act: -0.1699
Data Index: 1346954 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7043. Min Range: -6.7043
Max Act: 6.1887. Min Act: -0.1699
Data Index: 381757 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7043. Min Range: -6.7043
Max Act: 6.1731. Min Act: -0.1699
Data Index: 264370 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7043. Min Range: -6.7043
Max Act: 6.1262. Min Act: -0.1699
Data Index: 157212 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7043. Min Range: -6.7043
Max Act: 6.0793. Min Act: -0.1699
Data Index: 964521 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7043. Min Range: -6.7043
Max Act: 6.2043. Min Act: -0.1699
Data Index: 437006 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7043. Min Range: -6.7043
Max Act: 6.0325. Min Act: -0.1699
Data Index: 707369 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7043. Min Range: -6.7043
Max Act: 6.0950. Min Act: -0.1699
Data Index: 669163 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7043. Min Range: -6.7043
Max Act: 6.0168. Min Act: -0.1699
Data Index: 51737 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7043. Min Range: -6.7043
Max Act: 6.0012. Min Act: -0.1699
Data Index: 1049593 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7043. Min Range: -6.7043
Max Act: 6.0168. Min Act: -0.1699
Data Index: 822468 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19