Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1513 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.6028. Min Range: -4.6028
Max Act: 4.5716. Min Act: -0.1700
Data Index: 492766 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6028. Min Range: -4.6028
Max Act: 4.5716. Min Act: -0.1700
Data Index: 930848 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6028. Min Range: -4.6028
Max Act: 4.6028. Min Act: -0.1700
Data Index: 255177 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6028. Min Range: -4.6028
Max Act: 4.5403. Min Act: -0.1700
Data Index: 255793 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6028. Min Range: -4.6028
Max Act: 4.5403. Min Act: -0.1700
Data Index: 852099 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6028. Min Range: -4.6028
Max Act: 4.5090. Min Act: -0.1700
Data Index: 1340446 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6028. Min Range: -4.6028
Max Act: 4.5090. Min Act: -0.1700
Data Index: 1298577 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6028. Min Range: -4.6028
Max Act: 4.5090. Min Act: -0.1700
Data Index: 258591 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6028. Min Range: -4.6028
Max Act: 4.4465. Min Act: -0.1700
Data Index: 166799 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6028. Min Range: -4.6028
Max Act: 4.3840. Min Act: -0.1700
Data Index: 718913 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6028. Min Range: -4.6028
Max Act: 4.5090. Min Act: -0.1700
Data Index: 1108416 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6028. Min Range: -4.6028
Max Act: 4.5090. Min Act: -0.1700
Data Index: 743723 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6028. Min Range: -4.6028
Max Act: 4.4465. Min Act: -0.1700
Data Index: 314180 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6028. Min Range: -4.6028
Max Act: 4.4778. Min Act: -0.1700
Data Index: 349132 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6028. Min Range: -4.6028
Max Act: 4.5716. Min Act: -0.1700
Data Index: 238689 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6028. Min Range: -4.6028
Max Act: 4.4778. Min Act: -0.1700
Data Index: 372245 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6028. Min Range: -4.6028
Max Act: 4.4465. Min Act: -0.1700
Data Index: 629550 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6028. Min Range: -4.6028
Max Act: 4.4778. Min Act: -0.1700
Data Index: 810204 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6028. Min Range: -4.6028
Max Act: 4.4153. Min Act: -0.1700
Data Index: 173381 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6028. Min Range: -4.6028
Max Act: 4.4465. Min Act: -0.1700
Data Index: 224992 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19