Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 245 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.6882. Min Range: -2.6882
Max Act: 2.6882. Min Act: -0.1700
Data Index: 1087877 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6882. Min Range: -2.6882
Max Act: 2.6562. Min Act: -0.1700
Data Index: 1043796 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6882. Min Range: -2.6882
Max Act: 2.6401. Min Act: -0.1700
Data Index: 209742 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6882. Min Range: -2.6882
Max Act: 2.6401. Min Act: -0.1700
Data Index: 502814 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6882. Min Range: -2.6882
Max Act: 2.6080. Min Act: -0.1700
Data Index: 1010874 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6882. Min Range: -2.6882
Max Act: 2.5919. Min Act: -0.1700
Data Index: 963709 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6882. Min Range: -2.6882
Max Act: 2.5758. Min Act: -0.1700
Data Index: 844147 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6882. Min Range: -2.6882
Max Act: 2.5596. Min Act: -0.1700
Data Index: 1081338 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6882. Min Range: -2.6882
Max Act: 2.5758. Min Act: -0.1700
Data Index: 1081895 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6882. Min Range: -2.6882
Max Act: 2.5596. Min Act: -0.1700
Data Index: 1232870 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6882. Min Range: -2.6882
Max Act: 2.5596. Min Act: -0.1700
Data Index: 1288277 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6882. Min Range: -2.6882
Max Act: 2.5435. Min Act: -0.1700
Data Index: 533168 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6882. Min Range: -2.6882
Max Act: 2.5596. Min Act: -0.1700
Data Index: 611074 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6882. Min Range: -2.6882
Max Act: 2.5596. Min Act: -0.1700
Data Index: 1061100 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6882. Min Range: -2.6882
Max Act: 2.5596. Min Act: -0.1700
Data Index: 54619 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6882. Min Range: -2.6882
Max Act: 2.5596. Min Act: -0.1700
Data Index: 1143627 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6882. Min Range: -2.6882
Max Act: 2.5435. Min Act: -0.1700
Data Index: 960077 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6882. Min Range: -2.6882
Max Act: 2.5435. Min Act: -0.1700
Data Index: 263926 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6882. Min Range: -2.6882
Max Act: 2.5273. Min Act: -0.1700
Data Index: 962661 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6882. Min Range: -2.6882
Max Act: 2.5435. Min Act: -0.1700
Data Index: 1197830 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19