Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 93 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.1035. Min Range: -2.1035
Max Act: 2.1035. Min Act: -0.1700
Data Index: 811482 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1035. Min Range: -2.1035
Max Act: 2.0951. Min Act: -0.1700
Data Index: 1081268 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1035. Min Range: -2.1035
Max Act: 2.0951. Min Act: -0.1700
Data Index: 310099 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1035. Min Range: -2.1035
Max Act: 2.0868. Min Act: -0.1700
Data Index: 1027926 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1035. Min Range: -2.1035
Max Act: 2.0951. Min Act: -0.1700
Data Index: 759339 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1035. Min Range: -2.1035
Max Act: 2.0532. Min Act: -0.1700
Data Index: 82071 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1035. Min Range: -2.1035
Max Act: 2.0364. Min Act: -0.1700
Data Index: 467075 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1035. Min Range: -2.1035
Max Act: 2.0700. Min Act: -0.1700
Data Index: 915291 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1035. Min Range: -2.1035
Max Act: 2.0616. Min Act: -0.1700
Data Index: 1284131 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1035. Min Range: -2.1035
Max Act: 2.0364. Min Act: -0.1700
Data Index: 1074072 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1035. Min Range: -2.1035
Max Act: 2.0280. Min Act: -0.1700
Data Index: 1324526 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1035. Min Range: -2.1035
Max Act: 2.0280. Min Act: -0.1700
Data Index: 521287 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1035. Min Range: -2.1035
Max Act: 2.0195. Min Act: -0.1700
Data Index: 767125 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1035. Min Range: -2.1035
Max Act: 2.0364. Min Act: -0.1700
Data Index: 872588 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1035. Min Range: -2.1035
Max Act: 1.9942. Min Act: -0.1700
Data Index: 301217 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1035. Min Range: -2.1035
Max Act: 2.0364. Min Act: -0.1700
Data Index: 646781 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1035. Min Range: -2.1035
Max Act: 2.0195. Min Act: -0.1700
Data Index: 266582 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1035. Min Range: -2.1035
Max Act: 2.0195. Min Act: -0.1700
Data Index: 243480 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1035. Min Range: -2.1035
Max Act: 2.0280. Min Act: -0.1700
Data Index: 856263 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1035. Min Range: -2.1035
Max Act: 2.0195. Min Act: -0.1700
Data Index: 783501 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19