Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1514 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.6086. Min Range: -6.6086
Max Act: 6.6086. Min Act: -0.1700
Data Index: 403480 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6086. Min Range: -6.6086
Max Act: 6.4836. Min Act: -0.1700
Data Index: 360644 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6086. Min Range: -6.6086
Max Act: 6.4524. Min Act: -0.1700
Data Index: 438965 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6086. Min Range: -6.6086
Max Act: 6.2649. Min Act: -0.1700
Data Index: 913289 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6086. Min Range: -6.6086
Max Act: 6.3586. Min Act: -0.1700
Data Index: 445841 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6086. Min Range: -6.6086
Max Act: 6.2336. Min Act: -0.1700
Data Index: 995430 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6086. Min Range: -6.6086
Max Act: 6.2649. Min Act: -0.1700
Data Index: 647052 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6086. Min Range: -6.6086
Max Act: 6.2336. Min Act: -0.1700
Data Index: 1299929 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6086. Min Range: -6.6086
Max Act: 6.2024. Min Act: -0.1700
Data Index: 446163 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6086. Min Range: -6.6086
Max Act: 6.1711. Min Act: -0.1700
Data Index: 838128 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6086. Min Range: -6.6086
Max Act: 6.1086. Min Act: -0.1700
Data Index: 739424 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6086. Min Range: -6.6086
Max Act: 6.2649. Min Act: -0.1700
Data Index: 26882 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6086. Min Range: -6.6086
Max Act: 6.1086. Min Act: -0.1700
Data Index: 860664 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6086. Min Range: -6.6086
Max Act: 6.1711. Min Act: -0.1700
Data Index: 716594 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6086. Min Range: -6.6086
Max Act: 6.1086. Min Act: -0.1700
Data Index: 89774 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6086. Min Range: -6.6086
Max Act: 6.2024. Min Act: -0.1700
Data Index: 1146296 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6086. Min Range: -6.6086
Max Act: 6.1086. Min Act: -0.1700
Data Index: 718055 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6086. Min Range: -6.6086
Max Act: 6.1086. Min Act: -0.1700
Data Index: 901411 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6086. Min Range: -6.6086
Max Act: 6.0774. Min Act: -0.1700
Data Index: 539991 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6086. Min Range: -6.6086
Max Act: 6.0149. Min Act: -0.1700
Data Index: 344888 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19