Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1980 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.6610. Min Range: -2.6610
Max Act: 2.6610. Min Act: -0.1700
Data Index: 441061 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6610. Min Range: -2.6610
Max Act: 2.6289. Min Act: -0.1700
Data Index: 427667 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6610. Min Range: -2.6610
Max Act: 2.6289. Min Act: -0.1700
Data Index: 133811 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6610. Min Range: -2.6610
Max Act: 2.6129. Min Act: -0.1700
Data Index: 1196228 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6610. Min Range: -2.6610
Max Act: 2.5807. Min Act: -0.1700
Data Index: 486504 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6610. Min Range: -2.6610
Max Act: 2.5807. Min Act: -0.1700
Data Index: 793860 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6610. Min Range: -2.6610
Max Act: 2.5807. Min Act: -0.1700
Data Index: 566982 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6610. Min Range: -2.6610
Max Act: 2.5807. Min Act: -0.1700
Data Index: 983420 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6610. Min Range: -2.6610
Max Act: 2.5807. Min Act: -0.1700
Data Index: 1297828 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6610. Min Range: -2.6610
Max Act: 2.5646. Min Act: -0.1700
Data Index: 241101 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6610. Min Range: -2.6610
Max Act: 2.5646. Min Act: -0.1700
Data Index: 1123365 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6610. Min Range: -2.6610
Max Act: 2.5646. Min Act: -0.1700
Data Index: 594573 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6610. Min Range: -2.6610
Max Act: 2.5646. Min Act: -0.1700
Data Index: 750964 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6610. Min Range: -2.6610
Max Act: 2.5484. Min Act: -0.1700
Data Index: 772446 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6610. Min Range: -2.6610
Max Act: 2.5484. Min Act: -0.1700
Data Index: 1413622 (Python Code)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6610. Min Range: -2.6610
Max Act: 2.5484. Min Act: -0.1700
Data Index: 1146006 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6610. Min Range: -2.6610
Max Act: 2.5484. Min Act: -0.1700
Data Index: 234876 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6610. Min Range: -2.6610
Max Act: 2.5484. Min Act: -0.1700
Data Index: 1031020 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6610. Min Range: -2.6610
Max Act: 2.5484. Min Act: -0.1700
Data Index: 640557 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6610. Min Range: -2.6610
Max Act: 2.5484. Min Act: -0.1700
Data Index: 956182 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19