Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9130. Min Range: -2.9130
Max Act: 2.9130. Min Act: -0.1700
Data Index: 17021 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9130. Min Range: -2.9130
Max Act: 2.8812. Min Act: -0.1700
Data Index: 94365 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9130. Min Range: -2.9130
Max Act: 2.8653. Min Act: -0.1700
Data Index: 1170084 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9130. Min Range: -2.9130
Max Act: 2.8177. Min Act: -0.1700
Data Index: 12214 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9130. Min Range: -2.9130
Max Act: 2.8017. Min Act: -0.1700
Data Index: 1288377 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9130. Min Range: -2.9130
Max Act: 2.7699. Min Act: -0.1700
Data Index: 572215 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9130. Min Range: -2.9130
Max Act: 2.7858. Min Act: -0.1700
Data Index: 925719 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9130. Min Range: -2.9130
Max Act: 2.7539. Min Act: -0.1700
Data Index: 109666 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9130. Min Range: -2.9130
Max Act: 2.7539. Min Act: -0.1700
Data Index: 785203 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9130. Min Range: -2.9130
Max Act: 2.7539. Min Act: -0.1700
Data Index: 299469 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9130. Min Range: -2.9130
Max Act: 2.7539. Min Act: -0.1700
Data Index: 838319 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9130. Min Range: -2.9130
Max Act: 2.7379. Min Act: -0.1700
Data Index: 660575 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9130. Min Range: -2.9130
Max Act: 2.7379. Min Act: -0.1700
Data Index: 1109872 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9130. Min Range: -2.9130
Max Act: 2.7220. Min Act: -0.1700
Data Index: 1644950 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9130. Min Range: -2.9130
Max Act: 2.7220. Min Act: -0.1700
Data Index: 715830 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9130. Min Range: -2.9130
Max Act: 2.7220. Min Act: -0.1700
Data Index: 1135868 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9130. Min Range: -2.9130
Max Act: 2.7220. Min Act: -0.1700
Data Index: 178888 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9130. Min Range: -2.9130
Max Act: 2.7220. Min Act: -0.1700
Data Index: 966130 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9130. Min Range: -2.9130
Max Act: 2.7220. Min Act: -0.1700
Data Index: 795382 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9130. Min Range: -2.9130
Max Act: 2.7220. Min Act: -0.1700
Data Index: 945002 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19