Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 553 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8709. Min Range: -4.8709
Max Act: 4.8709. Min Act: -0.1700
Data Index: 41416 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8709. Min Range: -4.8709
Max Act: 4.6522. Min Act: -0.1700
Data Index: 1286126 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8709. Min Range: -4.8709
Max Act: 4.6522. Min Act: -0.1700
Data Index: 1123987 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8709. Min Range: -4.8709
Max Act: 4.6209. Min Act: -0.1700
Data Index: 824636 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8709. Min Range: -4.8709
Max Act: 4.6209. Min Act: -0.1700
Data Index: 171976 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8709. Min Range: -4.8709
Max Act: 4.6209. Min Act: -0.1700
Data Index: 625129 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8709. Min Range: -4.8709
Max Act: 4.6209. Min Act: -0.1700
Data Index: 1023541 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8709. Min Range: -4.8709
Max Act: 4.5897. Min Act: -0.1700
Data Index: 1321747 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8709. Min Range: -4.8709
Max Act: 4.5897. Min Act: -0.1700
Data Index: 82781 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8709. Min Range: -4.8709
Max Act: 4.5897. Min Act: -0.1700
Data Index: 432586 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8709. Min Range: -4.8709
Max Act: 4.5272. Min Act: -0.1700
Data Index: 930592 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8709. Min Range: -4.8709
Max Act: 4.5897. Min Act: -0.1700
Data Index: 118137 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8709. Min Range: -4.8709
Max Act: 4.5272. Min Act: -0.1700
Data Index: 249042 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8709. Min Range: -4.8709
Max Act: 4.5584. Min Act: -0.1700
Data Index: 753895 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8709. Min Range: -4.8709
Max Act: 4.4959. Min Act: -0.1700
Data Index: 1146611 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8709. Min Range: -4.8709
Max Act: 4.4959. Min Act: -0.1700
Data Index: 1047258 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8709. Min Range: -4.8709
Max Act: 4.5272. Min Act: -0.1700
Data Index: 142901 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8709. Min Range: -4.8709
Max Act: 4.4959. Min Act: -0.1700
Data Index: 955059 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8709. Min Range: -4.8709
Max Act: 4.5272. Min Act: -0.1700
Data Index: 1181552 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8709. Min Range: -4.8709
Max Act: 4.4959. Min Act: -0.1700
Data Index: 15330 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19